├── .clang-format ├── .gitignore ├── .gitmodules ├── LICENSE ├── README.md ├── audio_utils ├── CMakeLists.txt ├── audio_utils │ └── __init__.py ├── launch │ ├── test_beat_detector_node.launch.xml │ ├── test_capture_node.launch.xml │ ├── test_playback_node.launch.xml │ ├── test_python_nodes.launch.xml │ ├── test_resampling_node.launch.xml │ └── test_vad_node.launch.xml ├── models │ ├── SILERO_VAD_LICENSE │ └── silero_vad.onnx ├── package.xml ├── scripts │ ├── format_conversion_node.py │ ├── raw_file_writer_node.py │ ├── resampling_node.py │ └── split_channel_node.py └── src │ ├── PcmDevices │ ├── AlsaPcmDevice.cpp │ ├── AlsaPcmDevice.h │ ├── PcmDevice.cpp │ ├── PcmDevice.h │ ├── PulseAudioPcmDevice.cpp │ └── PulseAudioPcmDevice.h │ ├── Utils │ ├── AlsaException.cpp │ ├── AlsaException.h │ ├── PulseAudioException.cpp │ ├── PulseAudioException.h │ ├── Semaphore.cpp │ └── Semaphore.h │ ├── beat_detector_node.cpp │ ├── capture_node.cpp │ ├── playback_node.cpp │ └── vad_node.cpp ├── audio_utils_msgs ├── CMakeLists.txt ├── msg │ ├── AudioFrame.msg │ └── VoiceActivity.msg └── package.xml └── requirements.txt /.clang-format: -------------------------------------------------------------------------------- 1 | # LLVM 12 2 | --- 3 | BasedOnStyle: LLVM 4 | AccessModifierOffset: -4 5 | AlignAfterOpenBracket: AlwaysBreak 6 | AlignConsecutiveAssignments: None 7 | AlignConsecutiveBitFields: None 8 | AlignConsecutiveDeclarations: None 9 | AlignConsecutiveMacros: AcrossComments 10 | AlignEscapedNewlines: Right 11 | AlignOperands: Align 12 | AlignTrailingComments: false 13 | AllowAllArgumentsOnNextLine: false 14 | AllowAllConstructorInitializersOnNextLine: false 15 | AllowAllParametersOfDeclarationOnNextLine: false 16 | AllowShortBlocksOnASingleLine: Always 17 | AllowShortCaseLabelsOnASingleLine: false 18 | AllowShortEnumsOnASingleLine: false 19 | AllowShortFunctionsOnASingleLine: Inline 20 | AllowShortIfStatementsOnASingleLine: Never 21 | AllowShortLambdasOnASingleLine: All 22 | AllowShortLoopsOnASingleLine: false 23 | AlwaysBreakAfterReturnType: None 24 | AlwaysBreakBeforeMultilineStrings: false 25 | AlwaysBreakTemplateDeclarations: Yes 26 | AttributeMacros: [] 27 | BinPackArguments: false 28 | BinPackParameters: false 29 | BitFieldColonSpacing: After 30 | BreakBeforeBraces: Allman 31 | BreakBeforeBinaryOperators: None 32 | BreakBeforeConceptDeclarations: true 33 | BreakBeforeTernaryOperators: false 34 | BreakConstructorInitializers: BeforeColon 35 | BreakInheritanceList: BeforeColon 36 | BreakStringLiterals: true 37 | ColumnLimit: 120 38 | CompactNamespaces: false 39 | ConstructorInitializerAllOnOneLineOrOnePerLine: true 40 | ConstructorInitializerIndentWidth: 4 41 | ContinuationIndentWidth: 4 42 | Cpp11BracedListStyle: true 43 | DeriveLineEnding: false 44 | DerivePointerAlignment: false 45 | EmptyLineBeforeAccessModifier: LogicalBlock 46 | FixNamespaceComments: false 47 | ForEachMacros: [] 48 | IncludeBlocks: Preserve 49 | IndentCaseBlocks: false 50 | IndentCaseLabels: true 51 | IndentExternBlock: NoIndent 52 | IndentGotoLabels: true 53 | IndentPPDirectives: None 54 | IndentWidth: 4 55 | IndentWrappedFunctionNames: true 56 | KeepEmptyLinesAtTheStartOfBlocks: false 57 | Language: Cpp 58 | MaxEmptyLinesToKeep: 2 59 | NamespaceIndentation: All 60 | PointerAlignment: Left 61 | ReflowComments: true 62 | SortIncludes: false 63 | SortUsingDeclarations: false 64 | SpaceAfterCStyleCast: false 65 | SpaceAfterLogicalNot: false 66 | SpaceAfterTemplateKeyword: false 67 | SpaceAroundPointerQualifiers: Default 68 | SpaceBeforeAssignmentOperators: true 69 | SpaceBeforeCaseColon: false 70 | SpaceBeforeCpp11BracedList: false 71 | SpaceBeforeCtorInitializerColon: true 72 | SpaceBeforeInheritanceColon: true 73 | SpaceBeforeParens: ControlStatements 74 | SpaceBeforeRangeBasedForLoopColon: true 75 | SpaceBeforeSquareBrackets: false 76 | SpaceInEmptyBlock: false 77 | SpaceInEmptyParentheses: false 78 | SpacesBeforeTrailingComments: 2 79 | SpacesInAngles: Never 80 | SpacesInCStyleCastParentheses: false 81 | SpacesInConditionalStatement: false 82 | SpacesInContainerLiterals: false 83 | SpacesInParentheses: false 84 | SpacesInSquareBrackets: false 85 | Standard: c++14 86 | StatementAttributeLikeMacros: [emit] 87 | StatementMacros: [Q_UNUSED, Q_OBJECT] 88 | TabWidth: 4 89 | UseCRLF: false 90 | UseTab: Never 91 | MacroBlockBegin: "^QT_BEGIN_NAMESPACE" 92 | MacroBlockEnd: "QT_END_NAMESPACE$" 93 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | cmake-build-debug 3 | cmake-build-release 4 | build 5 | -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- 1 | [submodule "audio_utils/src/MusicBeatDetector"] 2 | path = audio_utils/src/MusicBeatDetector 3 | url = https://github.com/introlab/MusicBeatDetector.git 4 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # audio_utils 2 | 3 | ROS2 nodes and utilities for audio streams. 4 | 5 | For ROS1, please see the `ros1` branch. 6 | 7 | Author(s): Marc-Antoine Maheux 8 | 9 | ## Setup (Ubuntu) 10 | 11 | The following subsections explain how to use the library on Ubuntu. 12 | 13 | ### Install Dependencies 14 | 15 | ```bash 16 | sudo apt-get install cmake build-essential gfortran texinfo libasound2-dev libpulse-dev libgfortran-*-dev 17 | ``` 18 | 19 | ### Install Python Dependencies 20 | 21 | ```bash 22 | sudo pip install -r requirements.txt 23 | ``` 24 | 25 | or 26 | 27 | ```bash 28 | sudo pip3 install -r requirements.txt 29 | ``` 30 | 31 | ### Setup Submodules 32 | 33 | ```bash 34 | git submodule update --init --recursive 35 | ``` 36 | 37 | # Nodes 38 | 39 | ## `capture_node` 40 | 41 | This node captures the sound from an ALSA or PulseAudio device and publishes it to a topic. 42 | 43 | ### Parameters 44 | 45 | - `backend` (string): The backend to use (`alsa` or `pulse_audio`). 46 | The default value is `alsa`. 47 | - `device` (string): The device to capture (ex: `hw:CARD=1,DEV=0` or `default` for ALSA, or 48 | `alsa_input.usb-IntRoLab_16SoundsUSB_Audio_2.0-00.multichannel-input` for PulseAudio). 49 | The default value is `default`. 50 | - `format` (string): The audio format ( 51 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 52 | The default value is `signed_16`. 53 | - `channel_count` (int): The device channel count. The default value is `1`. 54 | - `sampling_frequency` (int): The device sampling frequency. The default value is `16000`. 55 | - `frame_sample_count` (int): The number of samples in each frame. The default value is `1024`. 56 | - `merge` (bool): Indicate to merge the channels or not. The default value is `false`. 57 | - `gain` (double): The gain to apply. The default value is `1.0`. 58 | - `latency_us` (int): The capture latency in microseconds. The default value is `64000`. 59 | - `channel_map` (Array of string): The PulseAudio channel mapping. If empty or omitted, the default mapping is used. 60 | This parameter must be set only with the PulseAudio backend. The default value is `[]`. 61 | - `queue_size` (int): The publisher queue size. The default value is `1`. 62 | 63 | ### Published Topics 64 | 65 | - `audio_out` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The 66 | captured sound. 67 | 68 | ## `playback_node` 69 | 70 | This node captures the sound from a topic and plays it to an ALSA or PulseAudio device. 71 | 72 | ### Parameters 73 | 74 | - `backend` (string): The backend to use (`alsa` or `pulse_audio`). 75 | The default value is `alsa`. 76 | - `device` (string): The device to capture (ex: `hw:CARD=1,DEV=0` or `default` for ALSA, or 77 | `alsa_input.usb-IntRoLab_16SoundsUSB_Audio_2.0-00.multichannel-input` for PulseAudio). 78 | The default value is `default`. 79 | - `format` (string): The audio format ( 80 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 81 | The default value is `signed_16`. 82 | - `channel_count` (int): The device channel count. The default value is `1`. 83 | - `sampling_frequency` (int): The device sampling frequency. The default value is `16000`. 84 | - `frame_sample_count` (int): The number of samples in each frame. The default value is `1024`. 85 | - `latency_us` (int): The capture latency in microseconds. The default value is `64000`. 86 | - `channel_map` (Array of string): The PulseAudio channel mapping. If empty or omitted, the default mapping is used. 87 | This parameter must be set only with the PulseAudio backend. The default value is `[]`. 88 | - `queue_size` (int): The publisher queue size. The default value is `1`. 89 | 90 | ### Subscribed Topics 91 | 92 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 93 | to play. 94 | 95 | ## `beat_detector_node` 96 | 97 | This node estimates the song tempo and detects if the beat is in the current frame. 98 | 99 | ### Parameters 100 | 101 | - `sampling_frequency` (int): The device sampling frequency. The default value is `44100`. 102 | - `frame_sample_count` (int): The number of samples in each analysed frame. It must be a multiple of `oss_fft_window_size`. 103 | The default value is `128`. 104 | - `oss_fft_window_size` (int): The onset strength signal window size. It must be greater than or equal to `frame_sample_count`. 105 | The default value is `1024`. 106 | - `flux_hamming_size` (int): The flux hamming window size to calculate the onset strength signal. The default value is `15`. 107 | - `oss_bpm_window_size` (int): The onset strength signal window size to calculate the BPM value. The default value is `1024`. 108 | - `min_bpm` (double): The minimum valid BPM value. The default value is `50`. 109 | - `max_bpm` (double): The maximum valid BPM value. The default value is `180`. 110 | - `bpm_candidate_count` (int): The number of cross-correlations to perform to find the best BPM. The default value is `10`. 111 | 112 | ### Subscribed Topics 113 | 114 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 115 | to analyze. The channel count must be 1. 116 | 117 | ### Published Topics 118 | 119 | - `bpm` (std_msgs/Float32): The tempo in bpm (beats per minute) for each frame. 120 | - `beat` (std_msgs/Bool): Indicate if the beat is in the current frame. 121 | 122 | ## `vad_node` 123 | 124 | This node performs voice activity detection with [Silero VAD](https://github.com/snakers4/silero-vad). 125 | The [models](models) folder contains the model trained by [Silero VAD](https://github.com/snakers4/silero-vad). The license of the model is [MIT](models/SILERO_VAD_LICENSE). 126 | 127 | ### Parameters 128 | 129 | - `silence_to_voice_threshold` (double): The threshold to detect voice activity when silence was previously detected. 130 | The default value is `0.5`. 131 | - `voice_to_silence_threshold` (double): The threshold to detect silence when voice activity was previously detected. 132 | It must be lower than `silence_to_voice_threshold`. The default value is `0.4`. 133 | - `min_silence_duration_ms` (double): The minimum silence duration in ms. 134 | The default value is `500`. 135 | 136 | ### Subscribed Topics 137 | 138 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 139 | to analyze. The channel count must be 1. The samply frequency must be 16000 Hz. The frame sample count must be a multiple of 512. 140 | 141 | ### Published Topics 142 | 143 | - `voice_activity` ([audio_utils_msgs/VoiceActivity](audio_utils_msgs/msg/VoiceActivity.msg)) The voice activity detection result. 144 | 145 | ## `format_conversion_node.py` 146 | 147 | This node converts the format of an audio topic. 148 | 149 | ### Parameters 150 | 151 | - `input_format` (string): The input audio format ( 152 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 153 | - `output_format` (string): The output audio format ( 154 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 155 | 156 | ### Subscribed Topics 157 | 158 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 159 | topic to convert. 160 | 161 | ### Published Topics 162 | 163 | - `audio_out` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The 164 | converted sound. 165 | 166 | ## `resampling_node.py` 167 | 168 | This node resamples an audio topic. 169 | 170 | ### Parameters 171 | 172 | - `input_format` (string): The input audio format ( 173 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 174 | - `output_format` (string): The output audio format ( 175 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 176 | - `channel_count` (int): The device channel count. 177 | - `input_sampling_frequency` (int): The input sampling frequency. 178 | - `output_sampling_frequency` (int): The output sampling frequency. 179 | - `input_frame_sample_count` (int): The number of samples in each frame of the input. 180 | - `dynamic_input_resampling` (bool: default is `false`): If `true`, always adjust the input sampling informations ( 181 | format, sampling frequency and frame sample count) to the sampling informations of the reveiced frames, dynamically. 182 | In this mode, `input_format`, `input_sampling_frequency` and `input_frame_sample_count` are not required, but they can 183 | be used to save a recomputation if the starting input sampling informations are known. 184 | 185 | ### Subscribed Topics 186 | 187 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 188 | topic to resample. 189 | 190 | ### Published Topics 191 | 192 | - `audio_out` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The 193 | resampled sound. 194 | 195 | ## `split_channel_node.py` 196 | 197 | This node split a multichannel audio topic into several mono audio topics. 198 | 199 | ### Parameters 200 | 201 | - `input_format` (string): The input audio format ( 202 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 203 | - `output_format` (string): The output audio format ( 204 | see [audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)). 205 | - `channel_count` (int): The device channel count. 206 | 207 | ### Subscribed Topics 208 | 209 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 210 | topic to split. 211 | 212 | ### Published Topics 213 | 214 | - `audio_out_0` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The 215 | first channel sound. 216 | - `audio_out_1` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The 217 | second channel sound. 218 | - ... 219 | 220 | ## `raw_file_writer_node.py` 221 | 222 | This node writes the raw sound data to a file. 223 | 224 | ### Parameters 225 | 226 | - `output_path` (string): The output file path. 227 | 228 | ### Subscribed Topics 229 | 230 | - `audio_in` ([audio_utils_msgs/AudioFrame](audio_utils_msgs/msg/AudioFrame.msg)) The sound 231 | topic to write. 232 | 233 | # License 234 | 235 | * [GPL-3.0 License ](LICENSE) 236 | 237 | # Sponsor 238 | 239 | ![IntRoLab](https://introlab.3it.usherbrooke.ca/IntRoLab.png) 240 | 241 | [IntRoLab - Intelligent / Interactive / Integrated / Interdisciplinary Robot Lab](https://introlab.3it.usherbrooke.ca) 242 | -------------------------------------------------------------------------------- /audio_utils/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | cmake_minimum_required(VERSION 3.5) 2 | project(audio_utils) 3 | 4 | 5 | # Default to C99 6 | if(NOT CMAKE_C_STANDARD) 7 | set(CMAKE_C_STANDARD 99) 8 | endif() 9 | 10 | # Default to C++17 11 | if(NOT CMAKE_CXX_STANDARD) 12 | set(CMAKE_CXX_STANDARD 17) 13 | endif() 14 | 15 | if(CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang") 16 | add_compile_options(-Wall -Wextra -Wpedantic) 17 | endif() 18 | 19 | set(MUSIC_BEAT_DETECTOR_ENABLE_TESTS OFF CACHE BOOL "") 20 | 21 | # Find dependencies 22 | find_package(ament_cmake REQUIRED) 23 | find_package(rclcpp REQUIRED) 24 | find_package(rclpy REQUIRED) 25 | find_package(audio_utils_msgs REQUIRED) 26 | find_package(ament_index_cpp REQUIRED) 27 | find_package(rosidl_default_generators REQUIRED) 28 | 29 | ## System dependencies are found with CMake's conventions 30 | 31 | # ******* ONNX Runtime dependency ******* 32 | if (EXISTS "/etc/nv_tegra_release") 33 | if (NOT EXISTS "/usr/local/lib/libonnxruntime.so") 34 | message(FATAL_ERROR "The ONNX Runtime is not installed.") 35 | endif() 36 | include_directories(SYSTEM /usr/local/include/onnxruntime/core/session) 37 | set(ONNXRUNTIME_LIBRARIES "/usr/local/lib/libonnxruntime.so") 38 | elseif(${CMAKE_HOST_SYSTEM_PROCESSOR} MATCHES "x86_64") 39 | set(ONNXRUNTIME_NAME "onnxruntime-linux-x64-1.15.1") 40 | elseif(${CMAKE_HOST_SYSTEM_PROCESSOR} MATCHES "aarch64") 41 | set(ONNXRUNTIME_NAME "onnxruntime-linux-aarch64-1.15.1") 42 | else() 43 | message(FATAL_ERROR "The CPU architecture is not supported.") 44 | endif() 45 | 46 | if (ONNXRUNTIME_NAME) 47 | if (NOT EXISTS ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}.tgz) 48 | file(DOWNLOAD https://github.com/microsoft/onnxruntime/releases/download/v1.15.1/${ONNXRUNTIME_NAME}.tgz ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}.tgz SHOW_PROGRESS) 49 | endif() 50 | if (NOT EXISTS ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}/VERSION_NUMBER) 51 | execute_process(COMMAND tar -xvf ${ONNXRUNTIME_NAME}.tgz WORKING_DIRECTORY ${CMAKE_BINARY_DIR}) 52 | endif() 53 | include_directories(SYSTEM ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}/include) 54 | set(ONNXRUNTIME_LIBRARIES ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}/lib/libonnxruntime.so) 55 | 56 | install(DIRECTORY ${CMAKE_BINARY_DIR}/${ONNXRUNTIME_NAME}/lib/ DESTINATION lib) 57 | endif() 58 | 59 | add_subdirectory(src/MusicBeatDetector) 60 | 61 | include_directories(SYSTEM 62 | src/MusicBeatDetector/MusicBeatDetector/include 63 | src/MusicBeatDetector/3rdParty/fftw/build/include 64 | src/MusicBeatDetector/3rdParty/armadillo-code/include 65 | src/MusicBeatDetector/3rdParty/OpenBLAS 66 | ) 67 | 68 | install(DIRECTORY src/MusicBeatDetector/MusicBeatDetector/include/ DESTINATION include) 69 | install(DIRECTORY src/MusicBeatDetector/3rdParty/fftw/build/include/ DESTINATION include) 70 | install(DIRECTORY src/MusicBeatDetector/3rdParty/armadillo-code/include/ DESTINATION include) 71 | install(DIRECTORY src/MusicBeatDetector/3rdParty/OpenBLAS/ DESTINATION include) 72 | install(TARGETS MusicBeatDetector DESTINATION lib) 73 | 74 | # C++ Nodes 75 | add_executable(beat_detector_node src/beat_detector_node.cpp) 76 | ament_target_dependencies(beat_detector_node rclcpp std_msgs audio_utils_msgs) 77 | target_link_libraries(beat_detector_node MusicBeatDetector) 78 | install(TARGETS beat_detector_node DESTINATION lib/${PROJECT_NAME}) 79 | 80 | 81 | add_executable(capture_node src/capture_node.cpp 82 | src/PcmDevices/PcmDevice.cpp 83 | src/PcmDevices/AlsaPcmDevice.cpp 84 | src/PcmDevices/PulseAudioPcmDevice.cpp 85 | src/Utils/AlsaException.cpp 86 | src/Utils/PulseAudioException.cpp 87 | ) 88 | ament_target_dependencies(capture_node rclcpp std_msgs audio_utils_msgs) 89 | target_link_libraries(capture_node MusicBeatDetector asound pulse-simple pulse) 90 | install(TARGETS capture_node DESTINATION lib/${PROJECT_NAME}) 91 | 92 | 93 | add_executable(playback_node src/playback_node.cpp 94 | src/PcmDevices/PcmDevice.cpp 95 | src/PcmDevices/AlsaPcmDevice.cpp 96 | src/PcmDevices/PulseAudioPcmDevice.cpp 97 | src/Utils/AlsaException.cpp 98 | src/Utils/PulseAudioException.cpp 99 | src/Utils/Semaphore.cpp 100 | ) 101 | ament_target_dependencies(playback_node rclcpp std_msgs audio_utils_msgs) 102 | target_link_libraries(playback_node MusicBeatDetector asound pulse-simple pulse) 103 | install(TARGETS playback_node DESTINATION lib/${PROJECT_NAME}) 104 | 105 | 106 | add_executable(vad_node src/vad_node.cpp) 107 | ament_target_dependencies(vad_node rclcpp std_msgs audio_utils_msgs ament_index_cpp) 108 | target_link_libraries(vad_node MusicBeatDetector ${ONNXRUNTIME_LIBRARIES}) 109 | install(TARGETS vad_node DESTINATION lib/${PROJECT_NAME}) 110 | install(DIRECTORY models DESTINATION share/${PROJECT_NAME}) 111 | 112 | 113 | # Python Nodes 114 | ament_python_install_package(${PROJECT_NAME}) 115 | 116 | install(PROGRAMS 117 | scripts/format_conversion_node.py 118 | scripts/raw_file_writer_node.py 119 | scripts/resampling_node.py 120 | scripts/split_channel_node.py 121 | DESTINATION lib/${PROJECT_NAME} 122 | ) 123 | 124 | # Launch files 125 | install(DIRECTORY launch DESTINATION share/${PROJECT_NAME}) 126 | 127 | # Exported libs 128 | ament_export_include_directories( 129 | include 130 | ${CMAKE_CURRENT_SOURCE_DIR}/src/MusicBeatDetector/MusicBeatDetector/include 131 | ${CMAKE_CURRENT_SOURCE_DIR}/src/MusicBeatDetector/3rdParty/fftw/build/include 132 | ${CMAKE_CURRENT_SOURCE_DIR}/src/MusicBeatDetector/3rdParty/armadillo-code/include 133 | ${CMAKE_CURRENT_SOURCE_DIR}/src/MusicBeatDetector/3rdParty/OpenBLAS 134 | ) 135 | ament_export_libraries( 136 | MusicBeatDetector 137 | MusicBeatDetector_openblas 138 | MusicBeatDetector_fftw 139 | ) 140 | 141 | ament_export_dependencies(audio_utils_msgs) 142 | 143 | ament_package() 144 | -------------------------------------------------------------------------------- /audio_utils/audio_utils/__init__.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | from audio_utils_msgs.msg import AudioFrame 4 | 5 | 6 | def get_format_information(format): 7 | if format == 'signed_8': 8 | return np.int8, 0, -np.iinfo(np.int8).min 9 | elif format == 'signed_16': 10 | return np.int16, 0, -np.iinfo(np.int16).min 11 | elif format == 'signed_24': 12 | raise NotImplementedError('signed_24 format is not supported') 13 | elif format == 'signed_padded_24': 14 | return np.int16, 0, 2**23 15 | elif format == 'signed_32': 16 | return np.int32, 0, -np.iinfo(np.int32).min 17 | 18 | elif format == 'unsigned_8': 19 | offset = np.iinfo(np.uint8).max // 2 20 | return np.uint8, -offset, offset 21 | elif format == 'unsigned_16': 22 | offset = np.iinfo(np.uint16).max // 2 23 | return np.uint16, -offset, offset 24 | elif format == 'unsigned_24': 25 | raise NotImplementedError('unsigned_24 format is not supported') 26 | elif format == 'unsigned_padded_24': 27 | offset = (2**24 - 1) // 2 28 | return np.uint32, -offset, offset 29 | elif format == 'unsigned_32': 30 | offset = np.iinfo(np.uint32).max // 2 31 | return np.uint32, -offset, offset 32 | 33 | elif format == 'float': 34 | return np.float32, 0, 1 35 | elif format == 'double': 36 | return np.float64, 0, 1 37 | else: 38 | raise ValueError('Invalid format ({})'.format(format)) 39 | 40 | 41 | def convert_audio_data_to_numpy_frames(format_information, channel_count, data): 42 | dtype, offset, scale = format_information 43 | frame = (np.frombuffer(data, dtype=dtype).astype(np.float64) + offset) / scale 44 | 45 | if channel_count == 1: 46 | return [frame] 47 | else: 48 | return _split_frame_by_channels(channel_count, frame) 49 | 50 | 51 | def _split_frame_by_channels(channel_count, frame): 52 | return [frame[i::channel_count] for i in range(channel_count)] 53 | 54 | 55 | def convert_numpy_frames_to_audio_data(format_information, frames): 56 | dtype, offset, scale = format_information 57 | 58 | if dtype == np.float32 or dtype == np.float64: 59 | min_value = -1.0 60 | max_value = 1.0 61 | else: 62 | min_value = np.iinfo(dtype).min 63 | max_value = np.iinfo(dtype).max 64 | 65 | frame = _merge_frames(frames) * scale - offset 66 | frame = np.clip(frame, a_min=min_value, a_max=max_value) 67 | return frame.astype(dtype).tobytes() 68 | 69 | 70 | def _merge_frames(frames): 71 | frame = np.zeros(frames[0].shape[0] * len(frames), dtype=np.float64) 72 | for i in range(len(frames)): 73 | frame[i::len(frames)] = frames[i] 74 | return frame 75 | -------------------------------------------------------------------------------- /audio_utils/launch/test_beat_detector_node.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | -------------------------------------------------------------------------------- /audio_utils/launch/test_capture_node.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | -------------------------------------------------------------------------------- /audio_utils/launch/test_playback_node.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | -------------------------------------------------------------------------------- /audio_utils/launch/test_python_nodes.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | -------------------------------------------------------------------------------- /audio_utils/launch/test_resampling_node.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | -------------------------------------------------------------------------------- /audio_utils/launch/test_vad_node.launch.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | -------------------------------------------------------------------------------- /audio_utils/models/SILERO_VAD_LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2020-present Silero Team 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /audio_utils/models/silero_vad.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/introlab/audio_utils/cfa851d947aee69a5dc590a35ec6b6ab25398a64/audio_utils/models/silero_vad.onnx -------------------------------------------------------------------------------- /audio_utils/package.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | audio_utils 5 | 0.0.0 6 | The audio_utils package 7 | Marc-Antoine Maheux 8 | GPL-3.0 license 9 | 10 | ament_cmake 11 | 12 | rclcpp 13 | rclpy 14 | ament_index_cpp 15 | 16 | audio_utils_msgs 17 | 18 | ros2launch 19 | 20 | ament_lint_auto 21 | ament_lint_common 22 | 23 | 24 | ament_cmake 25 | 26 | 27 | -------------------------------------------------------------------------------- /audio_utils/scripts/format_conversion_node.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import rclpy 4 | import rclpy.node 5 | 6 | from audio_utils_msgs.msg import AudioFrame 7 | from audio_utils import get_format_information, convert_audio_data_to_numpy_frames, convert_numpy_frames_to_audio_data 8 | 9 | 10 | class FormatConversionNode(rclpy.node.Node): 11 | def __init__(self): 12 | super().__init__('format_conversion_node') 13 | 14 | self._input_format = self.declare_parameter('input_format', '').get_parameter_value().string_value 15 | self._output_format = self.declare_parameter('output_format', '').get_parameter_value().string_value 16 | 17 | self._input_format_information = get_format_information(self._input_format) 18 | self._output_format_information = get_format_information(self._output_format) 19 | 20 | self._audio_frame_msg = AudioFrame() 21 | self._audio_pub = self.create_publisher(AudioFrame, 'audio_out', 10) 22 | self._audio_sub = self.create_subscription(AudioFrame, 'audio_in', self._audio_cb, 10) 23 | 24 | def _audio_cb(self, msg): 25 | if msg.format != self._input_format: 26 | self.get_logger().error( 27 | f'Invalid input format (msg.format={msg.format}, param.input_format={self._input_format})') 28 | return 29 | 30 | frames = convert_audio_data_to_numpy_frames(self._input_format_information, msg.channel_count, msg.data) 31 | data = convert_numpy_frames_to_audio_data(self._output_format_information, frames) 32 | 33 | self._audio_frame_msg.header = msg.header 34 | self._audio_frame_msg.format = self._output_format 35 | self._audio_frame_msg.channel_count = msg.channel_count 36 | self._audio_frame_msg.sampling_frequency = msg.sampling_frequency 37 | self._audio_frame_msg.frame_sample_count = msg.frame_sample_count 38 | self._audio_frame_msg.data = data 39 | 40 | self._audio_pub.publish(self._audio_frame_msg) 41 | 42 | def run(self): 43 | rclpy.spin(self) 44 | 45 | 46 | def main(): 47 | rclpy.init() 48 | format_conversion_node = FormatConversionNode() 49 | 50 | try: 51 | format_conversion_node.run() 52 | except KeyboardInterrupt: 53 | pass 54 | finally: 55 | format_conversion_node.destroy_node() 56 | if rclpy.ok(): 57 | rclpy.shutdown() 58 | 59 | 60 | if __name__ == '__main__': 61 | main() 62 | -------------------------------------------------------------------------------- /audio_utils/scripts/raw_file_writer_node.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import rclpy 4 | import rclpy.node 5 | 6 | from audio_utils_msgs.msg import AudioFrame 7 | 8 | 9 | class RawFileWriterNode(rclpy.node.Node): 10 | def __init__(self): 11 | super().__init__('raw_file_writer_node') 12 | 13 | self._output_path = self.declare_parameter('output_path', '').get_parameter_value().string_value 14 | 15 | self._file_descriptor = None 16 | self._audio_sub = self.create_subscription(AudioFrame, 'audio_in', self._audio_cb, 10) 17 | 18 | def _audio_cb(self, msg): 19 | if self._file_descriptor is None or self._file_descriptor.closed: 20 | return 21 | self._file_descriptor.write(msg.data) 22 | 23 | def run(self): 24 | with open(self._output_path, 'wb') as self._file_descriptor: 25 | rclpy.spin(self) 26 | 27 | 28 | def main(): 29 | rclpy.init() 30 | raw_file_writer_node = RawFileWriterNode() 31 | 32 | try: 33 | raw_file_writer_node.run() 34 | except KeyboardInterrupt: 35 | pass 36 | finally: 37 | raw_file_writer_node.destroy_node() 38 | if rclpy.ok(): 39 | rclpy.shutdown() 40 | 41 | 42 | if __name__ == '__main__': 43 | main() 44 | -------------------------------------------------------------------------------- /audio_utils/scripts/resampling_node.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import numpy as np 4 | import scipy.signal 5 | 6 | import rclpy 7 | import rclpy.node 8 | import rclpy.parameter 9 | 10 | from audio_utils_msgs.msg import AudioFrame 11 | from audio_utils import get_format_information, convert_audio_data_to_numpy_frames, convert_numpy_frames_to_audio_data 12 | from abc import ABC, abstractmethod 13 | 14 | 15 | class FrameInfo: 16 | def __init__(self, format: str, sampling_frequency: int, frame_sample_count: int, channel_count: int) -> None: 17 | self.format = format 18 | self.sampling_frequency = sampling_frequency 19 | self.format_information = get_format_information(format) 20 | self.frame_sample_count = frame_sample_count 21 | self.step = frame_sample_count // 2 22 | self.channel_count = channel_count 23 | 24 | @classmethod 25 | def from_audio_frame(cls, audio_frame: AudioFrame) -> 'FrameInfo': 26 | return cls(audio_frame.format, audio_frame.sampling_frequency, audio_frame.frame_sample_count, audio_frame.channel_count) 27 | 28 | def __eq__(self, other: object) -> bool: 29 | return ( 30 | isinstance(other, FrameInfo) and 31 | self.format == other.format and 32 | self.sampling_frequency == other.sampling_frequency and 33 | self.frame_sample_count == other.frame_sample_count and 34 | self.channel_count == other.channel_count 35 | ) 36 | 37 | 38 | class FrameConverter: 39 | def __init__(self, format: str, sampling_frequency: int, frame_sample_count: int, channel_count: int) -> None: 40 | self.frame_info = FrameInfo( 41 | format, sampling_frequency, frame_sample_count, channel_count) 42 | self.window = np.sqrt(scipy.signal.windows.hann(frame_sample_count)) 43 | self.buffer = np.zeros( 44 | (channel_count, int(self.frame_info.frame_sample_count * 3 / 2))) 45 | 46 | 47 | class InputFrameConverter(FrameConverter): 48 | def __init__(self, format: str, sampling_frequency: int, frame_sample_count: int, channel_count: int) -> None: 49 | super().__init__(format, sampling_frequency, frame_sample_count, channel_count) 50 | 51 | @classmethod 52 | def from_input_info(cls, input_frame_info: FrameInfo) -> 'InputFrameConverter': 53 | return cls(input_frame_info.format, input_frame_info.sampling_frequency, input_frame_info.frame_sample_count, input_frame_info.channel_count) 54 | 55 | 56 | class OutputFrameConverter(FrameConverter): 57 | def __init__(self, format: str, sampling_frequency: int, input_frame_info: FrameInfo) -> None: 58 | super().__init__( 59 | format, 60 | sampling_frequency, 61 | int(input_frame_info.frame_sample_count / 62 | input_frame_info.sampling_frequency * sampling_frequency), 63 | input_frame_info.channel_count 64 | ) 65 | 66 | @classmethod 67 | def from_output_info(cls, output_frame_info: FrameInfo, input_frame_info: FrameInfo) -> 'OutputFrameConverter': 68 | return cls(output_frame_info.format, output_frame_info.sampling_frequency, input_frame_info) 69 | 70 | 71 | class Resampler: 72 | def __init__(self, node: rclpy.node.Node, input_frame_converter: InputFrameConverter, output_frame_converter: OutputFrameConverter) -> None: 73 | self._input_frame_converter: InputFrameConverter = input_frame_converter 74 | self._output_frame_converter: OutputFrameConverter = output_frame_converter 75 | 76 | self._node = node 77 | 78 | self._set_rclpy_input_parameters( 79 | self._input_frame_converter.frame_info) 80 | 81 | self._audio_frame_msg = self._create_initialiazed_audio_frame_msg( 82 | self._output_frame_converter.frame_info) 83 | 84 | def resample(self, frame: AudioFrame) -> AudioFrame: 85 | input_frames = convert_audio_data_to_numpy_frames( 86 | self._input_frame_converter.frame_info.format_information, 87 | self._input_frame_converter.frame_info.channel_count, 88 | frame.data 89 | ) 90 | output_frames = [ 91 | self._resample_frame(input_frames[i], i) for i in range( 92 | self._input_frame_converter.frame_info.channel_count 93 | ) 94 | ] 95 | 96 | self._audio_frame_msg.header = frame.header 97 | self._audio_frame_msg.data = convert_numpy_frames_to_audio_data( 98 | self._output_frame_converter.frame_info.format_information, 99 | output_frames 100 | ) 101 | 102 | return self._audio_frame_msg 103 | 104 | @staticmethod 105 | def _create_initialiazed_audio_frame_msg(output_frame_info: FrameInfo) -> AudioFrame: 106 | audio_frame_msg = AudioFrame() 107 | audio_frame_msg.format = output_frame_info.format 108 | audio_frame_msg.channel_count = output_frame_info.channel_count 109 | audio_frame_msg.sampling_frequency = output_frame_info.sampling_frequency 110 | audio_frame_msg.frame_sample_count = output_frame_info.frame_sample_count 111 | return audio_frame_msg 112 | 113 | def _resample_frame(self, input_frame, i): 114 | self._input_frame_converter.buffer[i, 115 | self._input_frame_converter.frame_info.step:] = input_frame 116 | 117 | input_window1 = self._input_frame_converter.buffer[i, 118 | :self._input_frame_converter.frame_info.frame_sample_count] * self._input_frame_converter.window 119 | input_window2 = self._input_frame_converter.buffer[i, 120 | self._input_frame_converter.frame_info.step:] * self._input_frame_converter.window 121 | 122 | output_window1 = scipy.signal.resample( 123 | input_window1, self._output_frame_converter.frame_info.frame_sample_count) * self._output_frame_converter.window 124 | output_window2 = scipy.signal.resample( 125 | input_window2, self._output_frame_converter.frame_info.frame_sample_count) * self._output_frame_converter.window 126 | 127 | self._output_frame_converter.buffer[i, 128 | self._output_frame_converter.frame_info.step:] = 0 129 | self._output_frame_converter.buffer[i, 130 | :self._output_frame_converter.frame_info.frame_sample_count] += output_window1 131 | self._output_frame_converter.buffer[i, 132 | self._output_frame_converter.frame_info.step:] += output_window2 133 | 134 | self._input_frame_converter.buffer[i] = np.roll( 135 | self._input_frame_converter.buffer[i], self._input_frame_converter.frame_info.step) 136 | self._output_frame_converter.buffer[i] = np.roll( 137 | self._output_frame_converter.buffer[i], self._output_frame_converter.frame_info.step) 138 | 139 | return self._output_frame_converter.buffer[i, self._output_frame_converter.frame_info.step:] 140 | 141 | def is_same_input_frame_info(self, new_input_info: FrameInfo) -> bool: 142 | return self._input_frame_converter.frame_info == new_input_info 143 | 144 | @property 145 | def input_frame_info(self) -> FrameInfo: 146 | return self._input_frame_converter.frame_info 147 | 148 | def update_input_frame_info(self, new_input_info: FrameInfo) -> None: 149 | self._input_frame_converter = InputFrameConverter.from_input_info( 150 | new_input_info) 151 | self._output_frame_converter = OutputFrameConverter.from_output_info( 152 | self._output_frame_converter.frame_info, new_input_info) 153 | 154 | self._set_rclpy_input_parameters(new_input_info) 155 | 156 | self._audio_frame_msg = self._create_initialiazed_audio_frame_msg( 157 | self._output_frame_converter.frame_info) 158 | 159 | def _set_rclpy_input_parameters(self, new_input_info: FrameInfo) -> None: 160 | self._node.set_parameters([ 161 | rclpy.parameter.Parameter('input_format', rclpy.Parameter.Type.STRING, new_input_info.format), 162 | rclpy.parameter.Parameter('input_sampling_frequency', rclpy.Parameter.Type.INTEGER, new_input_info.sampling_frequency), 163 | rclpy.parameter.Parameter('input_frame_sample_count', rclpy.Parameter.Type.INTEGER, new_input_info.frame_sample_count), 164 | ]) 165 | 166 | 167 | class OnCallbackStrategy(ABC): 168 | def register_node(self, node: rclpy.node.Node) -> None: 169 | self._node = node 170 | 171 | self._node.declare_parameter('input_format', '') 172 | self._node.declare_parameter('input_sampling_frequency', 0) 173 | self._node.declare_parameter('input_frame_sample_count', 0) 174 | self._node.declare_parameter('channel_count', 1) 175 | 176 | self._node.declare_parameter('output_format', '') 177 | self._node.declare_parameter('output_sampling_frequency', 0) 178 | 179 | def _validate_node_registered(self) -> None: 180 | if not hasattr(self, '_node'): 181 | raise ValueError(f"Node not registered with strategy {self.__class__.__name__}") 182 | 183 | @abstractmethod 184 | def make_initial_input_frame_converter(self) -> InputFrameConverter: ... 185 | 186 | @abstractmethod 187 | def make_initial_output_frame_converter( 188 | self, input_frame_info: FrameInfo) -> OutputFrameConverter: ... 189 | 190 | @abstractmethod 191 | def audio_cb(self, msg: AudioFrame, resampler: Resampler, 192 | publisher: rclpy.node.Publisher) -> None: ... 193 | 194 | 195 | class StaticResamplingOnCallbackStrategy(OnCallbackStrategy): 196 | 197 | def make_initial_input_frame_converter(self) -> InputFrameConverter: 198 | self._validate_node_registered() 199 | return InputFrameConverter( 200 | format=self._node.get_parameter('input_format').get_parameter_value().string_value, 201 | sampling_frequency=self._node.get_parameter('input_sampling_frequency').get_parameter_value().integer_value, 202 | frame_sample_count=self._node.get_parameter('input_frame_sample_count').get_parameter_value().integer_value, 203 | channel_count=self._node.get_parameter('channel_count').get_parameter_value().integer_value, 204 | ) 205 | 206 | def make_initial_output_frame_converter(self, input_frame_info: FrameInfo) -> OutputFrameConverter: 207 | self._validate_node_registered() 208 | return OutputFrameConverter( 209 | format=self._node.get_parameter('output_format').get_parameter_value().string_value, 210 | sampling_frequency=self._node.get_parameter('output_sampling_frequency').get_parameter_value().integer_value, 211 | input_frame_info=input_frame_info, 212 | ) 213 | 214 | def audio_cb(self, msg: AudioFrame, resampler: Resampler, publisher: rclpy.node.Publisher) -> None: 215 | self._validate_node_registered() 216 | # We don't support changing the input frame info dynamically 217 | if not resampler.is_same_input_frame_info(FrameInfo.from_audio_frame(msg)): 218 | input_param = resampler.input_frame_info 219 | self._node.get_logger().error( 220 | f"Invalid frame (msg.format={msg.format}, input_param.format={input_param.format}, " 221 | f"msg.channel_count={msg.channel_count}, input_param.channel_count={input_param.channel_count}, " 222 | f"msg.sampling_frequency={msg.sampling_frequency}, input_param.sampling_frequency={input_param.sampling_frequency}, " 223 | f"msg.frame_sample_count={msg.frame_sample_count}, input_param.frame_sample_count={input_param.frame_sample_count})" 224 | ) 225 | return 226 | 227 | publisher.publish(resampler.resample(msg)) 228 | 229 | 230 | class DynamicResamplingOnCallbackStrategy(OnCallbackStrategy): 231 | def register_node(self, node: rclpy.node.Node) -> None: 232 | super().register_node(node) 233 | 234 | self._node.set_parameters([ 235 | rclpy.parameter.Parameter('input_format', rclpy.Parameter.Type.STRING, 'signed_16'), 236 | rclpy.parameter.Parameter('input_sampling_frequency', rclpy.Parameter.Type.INTEGER, 44100), 237 | rclpy.parameter.Parameter('input_frame_sample_count', rclpy.Parameter.Type.INTEGER, 480), 238 | rclpy.parameter.Parameter('channel_count', rclpy.Parameter.Type.INTEGER, 1), 239 | ]) 240 | 241 | def make_initial_input_frame_converter(self) -> InputFrameConverter: 242 | self._validate_node_registered() 243 | # Default are valid, they can be set to choose the starting values, or they will adjust when the first frame is received 244 | return InputFrameConverter( 245 | format=self._node.get_parameter('input_format').get_parameter_value().string_value, 246 | sampling_frequency=self._node.get_parameter('input_sampling_frequency').get_parameter_value().integer_value, 247 | frame_sample_count=self._node.get_parameter('input_frame_sample_count').get_parameter_value().integer_value, 248 | channel_count=self._node.get_parameter('channel_count').get_parameter_value().integer_value, 249 | ) 250 | 251 | def make_initial_output_frame_converter(self, input_frame_info: FrameInfo) -> OutputFrameConverter: 252 | self._validate_node_registered() 253 | return OutputFrameConverter( 254 | format=self._node.get_parameter('output_format').get_parameter_value().string_value, 255 | sampling_frequency=self._node.get_parameter('output_sampling_frequency').get_parameter_value().integer_value, 256 | input_frame_info=input_frame_info, 257 | ) 258 | 259 | def audio_cb(self, msg: AudioFrame, resampler: Resampler, publisher: rclpy.node.Publisher) -> None: 260 | self._validate_node_registered() 261 | # If input frame info has changed 262 | if not resampler.is_same_input_frame_info(FrameInfo.from_audio_frame(msg)): 263 | # We don't support changing the channel_count dynamically, it needs to stay the same 264 | if resampler.input_frame_info.channel_count != msg.channel_count: 265 | input_param = resampler.input_frame_info 266 | self._node.get_logger().error( 267 | f"Invalid channel_count: (msg.channel_count={msg.channel_count}, " 268 | f"input_param.channel_count={input_param.channel_count}) can't change dynamically") 269 | return 270 | 271 | # We update the input frame info 272 | resampler.update_input_frame_info(FrameInfo.from_audio_frame(msg)) 273 | 274 | publisher.publish(resampler.resample(msg)) 275 | 276 | 277 | class ResamplingNode(rclpy.node.Node): 278 | def __init__(self, resamplingStrategy: OnCallbackStrategy) -> None: 279 | super().__init__('resampling_node') 280 | 281 | self._resamplingStrategy = resamplingStrategy 282 | 283 | resamplingStrategy.register_node(self) 284 | 285 | self._input_info = resamplingStrategy.make_initial_input_frame_converter() 286 | 287 | self._output_info = resamplingStrategy.make_initial_output_frame_converter( 288 | self._input_info.frame_info) 289 | 290 | self._resampler = Resampler(self, 291 | input_frame_converter=self._input_info, output_frame_converter=self._output_info) 292 | 293 | self._audio_pub = self.create_publisher(AudioFrame, 'audio_out', 100) 294 | self._audio_sub = self.create_subscription(AudioFrame, 'audio_in', self._audio_cb, 100) 295 | 296 | def _audio_cb(self, msg: AudioFrame): 297 | self._resamplingStrategy.audio_cb( 298 | msg=msg, resampler=self._resampler, publisher=self._audio_pub) 299 | 300 | def run(self): 301 | rclpy.spin(self) 302 | 303 | 304 | class ResamplingNodeFactory(rclpy.node.Node): 305 | @staticmethod 306 | def create(): 307 | node = ResamplingNodeFactory('__resampling_node_factory') 308 | dynamic_input_resampling = ( 309 | node.declare_parameter('dynamic_input_resampling', False) 310 | .get_parameter_value().bool_value 311 | ) 312 | if dynamic_input_resampling: 313 | node.get_logger().info('Using dynamic resampling') 314 | node.destroy_node() 315 | return ResamplingNode(DynamicResamplingOnCallbackStrategy()) 316 | else: 317 | node.get_logger().info('Using static resampling') 318 | node.destroy_node() 319 | return ResamplingNode(StaticResamplingOnCallbackStrategy()) 320 | 321 | 322 | def main(): 323 | rclpy.init() 324 | resampling_node = ResamplingNodeFactory.create() 325 | 326 | try: 327 | resampling_node.run() 328 | except KeyboardInterrupt: 329 | pass 330 | finally: 331 | resampling_node.destroy_node() 332 | if rclpy.ok(): 333 | rclpy.shutdown() 334 | 335 | 336 | if __name__ == '__main__': 337 | main() 338 | -------------------------------------------------------------------------------- /audio_utils/scripts/split_channel_node.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import rclpy 4 | import rclpy.node 5 | 6 | from audio_utils_msgs.msg import AudioFrame 7 | from audio_utils import get_format_information, convert_audio_data_to_numpy_frames, convert_numpy_frames_to_audio_data 8 | 9 | 10 | class SplitChannelNode(rclpy.node.Node): 11 | def __init__(self): 12 | super().__init__('split_channel_node') 13 | 14 | self._input_format = self.declare_parameter('input_format', '').get_parameter_value().string_value 15 | self._output_format = self.declare_parameter('output_format', '').get_parameter_value().string_value 16 | self._channel_count = self.declare_parameter('channel_count', 0).get_parameter_value().integer_value 17 | 18 | self._input_format_information = get_format_information(self._input_format) 19 | self._output_format_information = get_format_information(self._output_format) 20 | 21 | self._audio_pubs = [self.create_publisher( 22 | AudioFrame, f'audio_out_{i}', 10) for i in range(self._channel_count)] 23 | self._audio_sub = self.create_subscription(AudioFrame, 'audio_in', self._audio_cb, 10) 24 | 25 | def _audio_cb(self, msg): 26 | if msg.format != self._input_format or msg.channel_count != self._channel_count: 27 | self.get_logger().error( 28 | f'Invalid frame (msg.format={msg.format}, msg.channel_count={msg.channel_count})') 29 | return 30 | 31 | frames = convert_audio_data_to_numpy_frames(self._input_format_information, msg.channel_count, msg.data) 32 | 33 | audio_frame_msg = AudioFrame() 34 | audio_frame_msg.header = msg.header 35 | audio_frame_msg.format = self._output_format 36 | audio_frame_msg.channel_count = 1 37 | audio_frame_msg.sampling_frequency = msg.sampling_frequency 38 | audio_frame_msg.frame_sample_count = msg.frame_sample_count 39 | 40 | for i in range(len(frames)): 41 | data = convert_numpy_frames_to_audio_data(self._output_format_information, [frames[i]]) 42 | audio_frame_msg.data = data 43 | self._audio_pubs[i].publish(audio_frame_msg) 44 | 45 | def run(self): 46 | rclpy.spin(self) 47 | 48 | 49 | def main(): 50 | rclpy.init() 51 | split_channel_node = SplitChannelNode() 52 | 53 | try: 54 | split_channel_node.run() 55 | except KeyboardInterrupt: 56 | pass 57 | finally: 58 | split_channel_node.destroy_node() 59 | if rclpy.ok(): 60 | rclpy.shutdown() 61 | 62 | 63 | if __name__ == '__main__': 64 | main() 65 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/AlsaPcmDevice.cpp: -------------------------------------------------------------------------------- 1 | #if defined(__unix__) || defined(__linux__) 2 | 3 | #include "AlsaPcmDevice.h" 4 | 5 | #include "../Utils/AlsaException.h" 6 | 7 | #include 8 | #include 9 | 10 | using namespace introlab; 11 | using namespace std; 12 | 13 | class PcmParamsDeleter 14 | { 15 | public: 16 | void operator()(snd_pcm_hw_params_t* handle) { snd_pcm_hw_params_free(handle); } 17 | }; 18 | 19 | AlsaPcmDevice::AlsaPcmDevice( 20 | const string& device, 21 | PcmDevice::Stream stream, 22 | PcmAudioFrameFormat format, 23 | size_t channelCount, 24 | size_t frameSampleCount, 25 | size_t sampleFrequency, 26 | unsigned int latencyUs) 27 | : PcmDevice(format, channelCount, frameSampleCount) 28 | { 29 | int err; 30 | snd_pcm_t* pcmHandlePointer; 31 | snd_pcm_hw_params_t* paramsPointer; 32 | 33 | if ((err = snd_pcm_open(&pcmHandlePointer, device.c_str(), convert(stream), 0)) < 0) 34 | { 35 | THROW_ALSA_EXCEPTION("Cannot open audio device: " + device, err, snd_strerror(err)); 36 | } 37 | 38 | unique_ptr pcmHandle(pcmHandlePointer); 39 | 40 | if ((err = snd_pcm_hw_params_malloc(¶msPointer)) < 0) 41 | { 42 | THROW_ALSA_EXCEPTION("Cannot allocate hardware parameter structure", err, snd_strerror(err)); 43 | } 44 | 45 | unique_ptr params(paramsPointer); 46 | 47 | if ((err = snd_pcm_hw_params_any(pcmHandle.get(), params.get())) < 0) 48 | { 49 | THROW_ALSA_EXCEPTION("Cannot initialize hardware parameter structure", err, snd_strerror(err)); 50 | } 51 | 52 | if ((err = snd_pcm_hw_params_set_access(pcmHandle.get(), params.get(), SND_PCM_ACCESS_RW_INTERLEAVED)) < 0) 53 | { 54 | THROW_ALSA_EXCEPTION("Cannot set access type", err, snd_strerror(err)); 55 | } 56 | 57 | if ((err = snd_pcm_hw_params_set_format(pcmHandle.get(), params.get(), convert(format))) < 0) 58 | { 59 | THROW_ALSA_EXCEPTION("Cannot set sample format", err, snd_strerror(err)); 60 | } 61 | 62 | if ((err = snd_pcm_hw_params_set_rate(pcmHandle.get(), params.get(), static_cast(sampleFrequency), 0)) < 0) 63 | { 64 | THROW_ALSA_EXCEPTION("Cannot set sample rate", err, snd_strerror(err)); 65 | } 66 | 67 | if ((err = snd_pcm_hw_params_set_channels(pcmHandle.get(), params.get(), static_cast(channelCount))) < 0) 68 | { 69 | THROW_ALSA_EXCEPTION("Cannot set channel count", err, snd_strerror(err)); 70 | } 71 | 72 | snd_pcm_uframes_t periodSize = static_cast(frameSampleCount); 73 | if ((err = snd_pcm_hw_params_set_period_size(pcmHandle.get(), params.get(), periodSize, 0)) < 0) 74 | { 75 | THROW_ALSA_EXCEPTION("Cannot set period size", err, snd_strerror(err)); 76 | } 77 | 78 | if ((err = snd_pcm_hw_params_set_buffer_time_near(pcmHandle.get(), params.get(), &latencyUs, NULL)) < 0) 79 | { 80 | THROW_ALSA_EXCEPTION("Cannot set buffer time", err, snd_strerror(err)); 81 | } 82 | 83 | if ((err = snd_pcm_hw_params(pcmHandle.get(), params.get())) < 0) 84 | { 85 | THROW_ALSA_EXCEPTION("Cannot set parameters", err, snd_strerror(err)); 86 | } 87 | 88 | if ((err = snd_pcm_prepare(pcmHandle.get())) < 0) 89 | { 90 | THROW_ALSA_EXCEPTION("Cannot prepare audio interface for use", err, snd_strerror(err)); 91 | } 92 | 93 | m_pcmHandle = move(pcmHandle); 94 | } 95 | 96 | AlsaPcmDevice::~AlsaPcmDevice() {} 97 | 98 | void AlsaPcmDevice::read(PcmAudioFrame& frame) 99 | { 100 | PcmDevice::read(frame); 101 | 102 | snd_pcm_uframes_t periodSize = static_cast(m_frameSampleCount); 103 | int err = snd_pcm_readi(m_pcmHandle.get(), frame.data(), periodSize); 104 | 105 | if (err == -EPIPE) 106 | { 107 | // EPIPE means overrun 108 | err = snd_pcm_recover(m_pcmHandle.get(), err, 1); 109 | if (err >= 0) 110 | { 111 | err = snd_pcm_readi(m_pcmHandle.get(), frame.data(), periodSize); 112 | } 113 | } 114 | 115 | if (static_cast(err) != periodSize) 116 | { 117 | THROW_ALSA_EXCEPTION("Read from audio interface failed", err, snd_strerror(err)); 118 | } 119 | } 120 | 121 | void AlsaPcmDevice::write(const PcmAudioFrame& frame) 122 | { 123 | PcmDevice::write(frame); 124 | 125 | snd_pcm_uframes_t periodSize = static_cast(m_frameSampleCount); 126 | int err = snd_pcm_writei(m_pcmHandle.get(), frame.data(), periodSize); 127 | 128 | if (err == -EPIPE) 129 | { 130 | // EPIPE means underrun 131 | err = snd_pcm_recover(m_pcmHandle.get(), err, 1); 132 | if (err >= 0) 133 | { 134 | err = snd_pcm_writei(m_pcmHandle.get(), frame.data(), periodSize); 135 | } 136 | } 137 | 138 | if (static_cast(err) != periodSize) 139 | { 140 | THROW_ALSA_EXCEPTION("Write to audio interface failed", err, snd_strerror(err)); 141 | } 142 | } 143 | 144 | void AlsaPcmDevice::wait() 145 | { 146 | int err = snd_pcm_wait(m_pcmHandle.get(), -1); 147 | if (err != 1) 148 | { 149 | THROW_ALSA_EXCEPTION("snd_pcm_wait failed", err, snd_strerror(err)); 150 | } 151 | } 152 | 153 | snd_pcm_stream_t AlsaPcmDevice::convert(PcmDevice::Stream stream) 154 | { 155 | switch (stream) 156 | { 157 | case PcmDevice::Stream::Playback: 158 | return SND_PCM_STREAM_PLAYBACK; 159 | case PcmDevice::Stream::Capture: 160 | return SND_PCM_STREAM_CAPTURE; 161 | } 162 | 163 | THROW_NOT_SUPPORTED_EXCEPTION("Not supported stream"); 164 | } 165 | 166 | snd_pcm_format_t AlsaPcmDevice::convert(PcmAudioFrameFormat format) 167 | { 168 | static const map Mapping( 169 | {{PcmAudioFrameFormat::Signed8, SND_PCM_FORMAT_S8}, 170 | {PcmAudioFrameFormat::Signed16, SND_PCM_FORMAT_S16_LE}, 171 | {PcmAudioFrameFormat::Signed24, SND_PCM_FORMAT_S24_LE}, 172 | {PcmAudioFrameFormat::Signed32, SND_PCM_FORMAT_S32_LE}, 173 | 174 | {PcmAudioFrameFormat::Unsigned8, SND_PCM_FORMAT_U8}, 175 | {PcmAudioFrameFormat::Unsigned16, SND_PCM_FORMAT_U16_LE}, 176 | {PcmAudioFrameFormat::Unsigned24, SND_PCM_FORMAT_U24_LE}, 177 | {PcmAudioFrameFormat::Unsigned32, SND_PCM_FORMAT_U32_LE}, 178 | 179 | {PcmAudioFrameFormat::Float, SND_PCM_FORMAT_FLOAT_LE}, 180 | {PcmAudioFrameFormat::Double, SND_PCM_FORMAT_FLOAT64_LE}}); 181 | 182 | auto it = Mapping.find(format); 183 | if (it != Mapping.end()) 184 | { 185 | return it->second; 186 | } 187 | 188 | THROW_NOT_SUPPORTED_EXCEPTION("Not supported format"); 189 | } 190 | 191 | #endif 192 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/AlsaPcmDevice.h: -------------------------------------------------------------------------------- 1 | #ifndef PCM_DEVICES_ALSA_PCM_DEVICE_H 2 | #define PCM_DEVICES_ALSA_PCM_DEVICE_H 3 | 4 | #if defined(__unix__) || defined(__linux__) 5 | 6 | #include "PcmDevice.h" 7 | 8 | #include 9 | #include 10 | 11 | #include 12 | 13 | #include 14 | #include 15 | 16 | namespace introlab 17 | { 18 | class AlsaPcmDevice : public PcmDevice 19 | { 20 | class PcmDeleter 21 | { 22 | public: 23 | void operator()(snd_pcm_t* handle) { snd_pcm_close(handle); } 24 | }; 25 | 26 | std::unique_ptr m_pcmHandle; 27 | 28 | public: 29 | AlsaPcmDevice( 30 | const std::string& device, 31 | PcmDevice::Stream stream, 32 | PcmAudioFrameFormat format, 33 | std::size_t channelCount, 34 | std::size_t frameSampleCount, 35 | std::size_t sampleFrequency, 36 | unsigned int latencyUs); 37 | ~AlsaPcmDevice() override; 38 | 39 | DECLARE_NOT_COPYABLE(AlsaPcmDevice); 40 | DECLARE_NOT_MOVABLE(AlsaPcmDevice); 41 | 42 | void read(PcmAudioFrame& frame) override; 43 | void write(const PcmAudioFrame& frame) override; 44 | void wait() override; 45 | 46 | private: 47 | static snd_pcm_stream_t convert(PcmDevice::Stream stream); 48 | static snd_pcm_format_t convert(PcmAudioFrameFormat format); 49 | }; 50 | } 51 | 52 | #else 53 | 54 | #error "Invalid include file" 55 | 56 | #endif 57 | 58 | #endif 59 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/PcmDevice.cpp: -------------------------------------------------------------------------------- 1 | #if defined(__unix__) || defined(__linux__) 2 | 3 | #include "PcmDevice.h" 4 | 5 | #include 6 | 7 | using namespace introlab; 8 | using namespace std; 9 | 10 | PcmDevice::PcmDevice(PcmAudioFrameFormat format, size_t channelCount, size_t frameSampleCount) 11 | : m_format(format), 12 | m_channelCount(channelCount), 13 | m_frameSampleCount(frameSampleCount) 14 | { 15 | } 16 | 17 | PcmDevice::~PcmDevice() {} 18 | 19 | void PcmDevice::read(PcmAudioFrame& frame) 20 | { 21 | if (frame.format() != m_format || frame.channelCount() != m_channelCount || 22 | frame.sampleCount() != m_frameSampleCount) 23 | { 24 | THROW_INVALID_VALUE_EXCEPTION("format, channelCount, sampleCount", ""); 25 | } 26 | } 27 | 28 | void PcmDevice::write(const PcmAudioFrame& frame) 29 | { 30 | if (frame.format() != m_format || frame.channelCount() != m_channelCount || 31 | frame.sampleCount() != m_frameSampleCount) 32 | { 33 | THROW_INVALID_VALUE_EXCEPTION("format, channelCount, sampleCount", ""); 34 | } 35 | } 36 | 37 | PcmDevice::Backend PcmDevice::parseBackend(const string& backend) 38 | { 39 | if (backend == "alsa") 40 | { 41 | return PcmDevice::Backend::Alsa; 42 | } 43 | else if (backend == "pulse_audio") 44 | { 45 | return PcmDevice::Backend::PulseAudio; 46 | } 47 | 48 | THROW_INVALID_VALUE_EXCEPTION("backend", backend); 49 | } 50 | 51 | #endif 52 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/PcmDevice.h: -------------------------------------------------------------------------------- 1 | #ifndef PCM_DEVICES_PCM_DEVICE_H 2 | #define PCM_DEVICES_PCM_DEVICE_H 3 | 4 | #if defined(__unix__) || defined(__linux__) 5 | 6 | #include 7 | #include 8 | 9 | namespace introlab 10 | { 11 | class PcmDevice 12 | { 13 | public: 14 | enum class Stream 15 | { 16 | Playback, 17 | Capture 18 | }; 19 | 20 | enum class Backend 21 | { 22 | Alsa, 23 | PulseAudio 24 | }; 25 | 26 | protected: 27 | PcmAudioFrameFormat m_format; 28 | std::size_t m_channelCount; 29 | std::size_t m_frameSampleCount; 30 | 31 | public: 32 | PcmDevice(PcmAudioFrameFormat format, std::size_t channelCount, std::size_t frameSampleCount); 33 | virtual ~PcmDevice(); 34 | 35 | DECLARE_NOT_COPYABLE(PcmDevice); 36 | DECLARE_NOT_MOVABLE(PcmDevice); 37 | 38 | virtual void read(PcmAudioFrame& frame); 39 | virtual void write(const PcmAudioFrame& frame); 40 | virtual void wait() = 0; 41 | 42 | static Backend parseBackend(const std::string& backend); 43 | }; 44 | } 45 | 46 | #else 47 | 48 | #error "Invalid include file" 49 | 50 | #endif 51 | 52 | #endif 53 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/PulseAudioPcmDevice.cpp: -------------------------------------------------------------------------------- 1 | #if defined(__unix__) || defined(__linux__) 2 | 3 | #include "PulseAudioPcmDevice.h" 4 | 5 | #include "../Utils/PulseAudioException.h" 6 | 7 | #include 8 | #include 9 | #include 10 | 11 | using namespace introlab; 12 | using namespace std; 13 | 14 | PulseAudioPcmDevice::PulseAudioPcmDevice( 15 | const string& device, 16 | PcmDevice::Stream stream, 17 | PcmAudioFrameFormat format, 18 | size_t channelCount, 19 | size_t frameSampleCount, 20 | size_t sampleFrequency, 21 | uint64_t latencyUs, 22 | const vector& channelMap) 23 | : PcmDevice(format, channelCount, frameSampleCount) 24 | { 25 | pa_sample_spec ss; 26 | ss.format = convert(format); 27 | ss.rate = static_cast(sampleFrequency); 28 | ss.channels = static_cast(channelCount); 29 | 30 | setChannelMap(channelCount, channelMap); 31 | 32 | pa_buffer_attr ba; 33 | ba.maxlength = -1; 34 | ba.tlength = (stream == PcmDevice::Stream::Playback) ? pa_usec_to_bytes(latencyUs, &ss) : -1; 35 | ba.prebuf = -1; 36 | ba.minreq = -1; 37 | ba.fragsize = (stream == PcmDevice::Stream::Capture) ? pa_usec_to_bytes(latencyUs, &ss) : -1; 38 | 39 | int error = 0; 40 | 41 | m_paHandle = unique_ptr(pa_simple_new( 42 | nullptr, 43 | "audio_utils", 44 | convert(stream), 45 | device.c_str(), 46 | "audio_utils", 47 | &ss, 48 | m_channelMap.get(), 49 | &ba, 50 | &error)); 51 | if (!m_paHandle) 52 | { 53 | THROW_PULSE_AUDIO_EXCEPTION("Cannot open audio device: " + device, error, pa_strerror(error)); 54 | } 55 | } 56 | 57 | PulseAudioPcmDevice::~PulseAudioPcmDevice() {} 58 | 59 | void PulseAudioPcmDevice::read(PcmAudioFrame& frame) 60 | { 61 | PcmDevice::read(frame); 62 | 63 | int error = 0; 64 | if (pa_simple_read(m_paHandle.get(), frame.data(), frame.size(), &error) < 0) 65 | { 66 | THROW_PULSE_AUDIO_EXCEPTION("Read from pulse audio failed", error, pa_strerror(error)); 67 | } 68 | } 69 | 70 | void PulseAudioPcmDevice::write(const PcmAudioFrame& frame) 71 | { 72 | PcmDevice::write(frame); 73 | 74 | int error = 0; 75 | if (pa_simple_write(m_paHandle.get(), frame.data(), frame.size(), &error) < 0) 76 | { 77 | THROW_PULSE_AUDIO_EXCEPTION("Write to pulse audio failed", error, pa_strerror(error)); 78 | } 79 | } 80 | 81 | void PulseAudioPcmDevice::wait() {} 82 | 83 | void PulseAudioPcmDevice::setChannelMap(size_t channelCount, const vector& channelMap) 84 | { 85 | if (channelMap.empty()) 86 | { 87 | return; 88 | } 89 | else if (channelMap.size() != channelCount) 90 | { 91 | THROW_INVALID_VALUE_EXCEPTION("channelMap", ""); 92 | } 93 | 94 | m_channelMap = make_unique(); 95 | pa_channel_map_init(m_channelMap.get()); 96 | 97 | m_channelMap->channels = channelCount; 98 | for (size_t i = 0; i < channelCount; i++) 99 | { 100 | m_channelMap->map[i] = pa_channel_position_from_string(channelMap[i].c_str()); 101 | if (m_channelMap->map[i] == PA_CHANNEL_POSITION_INVALID) 102 | { 103 | THROW_INVALID_VALUE_EXCEPTION("channelMap[" + to_string(i) + "]", channelMap[i]); 104 | } 105 | } 106 | 107 | if (!pa_channel_map_valid(m_channelMap.get())) 108 | { 109 | THROW_PULSE_AUDIO_EXCEPTION("Not valid channel map", 0, ""); 110 | } 111 | } 112 | 113 | pa_stream_direction_t PulseAudioPcmDevice::convert(PcmDevice::Stream stream) 114 | { 115 | switch (stream) 116 | { 117 | case PcmDevice::Stream::Playback: 118 | return PA_STREAM_PLAYBACK; 119 | case PcmDevice::Stream::Capture: 120 | return PA_STREAM_RECORD; 121 | } 122 | 123 | THROW_NOT_SUPPORTED_EXCEPTION("Not supported stream"); 124 | } 125 | 126 | pa_sample_format_t PulseAudioPcmDevice::convert(PcmAudioFrameFormat format) 127 | { 128 | static const map Mapping( 129 | {{PcmAudioFrameFormat::Signed16, PA_SAMPLE_S16LE}, 130 | {PcmAudioFrameFormat::Signed24, PA_SAMPLE_S24LE}, 131 | {PcmAudioFrameFormat::SignedPadded24, PA_SAMPLE_S24_32LE}, 132 | {PcmAudioFrameFormat::Signed32, PA_SAMPLE_S32LE}, 133 | 134 | {PcmAudioFrameFormat::Unsigned8, PA_SAMPLE_U8}, 135 | 136 | {PcmAudioFrameFormat::Float, PA_SAMPLE_FLOAT32LE}}); 137 | 138 | auto it = Mapping.find(format); 139 | if (it != Mapping.end()) 140 | { 141 | return it->second; 142 | } 143 | 144 | THROW_NOT_SUPPORTED_EXCEPTION("Not supported format"); 145 | } 146 | 147 | #endif 148 | -------------------------------------------------------------------------------- /audio_utils/src/PcmDevices/PulseAudioPcmDevice.h: -------------------------------------------------------------------------------- 1 | #ifndef PCM_DEVICES_PULSE_AUDIO_PCM_DEVICE_H 2 | #define PCM_DEVICES_PULSE_AUDIO_PCM_DEVICE_H 3 | 4 | #if defined(__unix__) || defined(__linux__) 5 | 6 | #include "PcmDevice.h" 7 | 8 | #include 9 | #include 10 | 11 | #include 12 | #include 13 | 14 | #include 15 | #include 16 | #include 17 | 18 | namespace introlab 19 | { 20 | class PulseAudioPcmDevice : public PcmDevice 21 | { 22 | class PaDeleter 23 | { 24 | public: 25 | void operator()(pa_simple* handle) { pa_simple_free(handle); } 26 | }; 27 | 28 | std::unique_ptr m_paHandle; 29 | std::unique_ptr m_channelMap; 30 | 31 | public: 32 | PulseAudioPcmDevice( 33 | const std::string& device, 34 | PcmDevice::Stream stream, 35 | PcmAudioFrameFormat format, 36 | std::size_t channelCount, 37 | std::size_t frameSampleCount, 38 | std::size_t sampleFrequency, 39 | uint64_t latencyUs, 40 | const std::vector& channelMap); 41 | ~PulseAudioPcmDevice() override; 42 | 43 | DECLARE_NOT_COPYABLE(PulseAudioPcmDevice); 44 | DECLARE_NOT_MOVABLE(PulseAudioPcmDevice); 45 | 46 | void read(PcmAudioFrame& frame) override; 47 | void write(const PcmAudioFrame& frame) override; 48 | void wait() override; 49 | 50 | private: 51 | void setChannelMap(std::size_t channelCount, const std::vector& channelMap); 52 | 53 | static pa_stream_direction_t convert(PcmDevice::Stream stream); 54 | static pa_sample_format_t convert(PcmAudioFrameFormat format); 55 | }; 56 | } 57 | 58 | #else 59 | 60 | #error "Invalid include file" 61 | 62 | #endif 63 | 64 | #endif 65 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/AlsaException.cpp: -------------------------------------------------------------------------------- 1 | #if defined(__unix__) || defined(__linux__) 2 | 3 | #include "AlsaException.h" 4 | 5 | using namespace introlab; 6 | using namespace std; 7 | 8 | AlsaException::AlsaException( 9 | const string& filename, 10 | const string& function, 11 | int line, 12 | const string& message, 13 | int errorCode, 14 | const string& errorDescription) 15 | : runtime_error( 16 | "[" + filename + ", " + function + ", " + to_string(line) + "] : AlsaException: " + message + " (" + 17 | to_string(errorCode) + ": " + errorDescription + ")") 18 | { 19 | } 20 | 21 | AlsaException::~AlsaException() {} 22 | 23 | #endif 24 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/AlsaException.h: -------------------------------------------------------------------------------- 1 | #ifndef UTILS_ALSA_EXCEPTION_H 2 | #define UTILS_ALSA_EXCEPTION_H 3 | 4 | #if defined(__unix__) || defined(__linux__) 5 | 6 | #include 7 | 8 | #define THROW_ALSA_EXCEPTION(message, errorCode, errorDescription) \ 9 | throw introlab::AlsaException( \ 10 | __FILENAME__, \ 11 | __LOGGED_FUNCTION__, \ 12 | __LINE__, \ 13 | (message), \ 14 | (errorCode), \ 15 | (errorDescription)) 16 | 17 | namespace introlab 18 | { 19 | class AlsaException : public std::runtime_error 20 | { 21 | public: 22 | AlsaException( 23 | const std::string& filename, 24 | const std::string& function, 25 | int line, 26 | const std::string& message, 27 | int errorCode, 28 | const std::string& errorDescription); 29 | 30 | ~AlsaException() override; 31 | }; 32 | } 33 | 34 | #else 35 | 36 | #error "Invalid include file" 37 | 38 | #endif 39 | 40 | #endif 41 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/PulseAudioException.cpp: -------------------------------------------------------------------------------- 1 | #if defined(__unix__) || defined(__linux__) 2 | 3 | #include "PulseAudioException.h" 4 | 5 | using namespace introlab; 6 | using namespace std; 7 | 8 | PulseAudioException::PulseAudioException( 9 | const string& filename, 10 | const string& function, 11 | int line, 12 | const string& message, 13 | int errorCode, 14 | const string& errorDescription) 15 | : runtime_error( 16 | "[" + filename + ", " + function + ", " + to_string(line) + "] : PulseAudioException: " + message + " (" + 17 | to_string(errorCode) + ": " + errorDescription + ")") 18 | { 19 | } 20 | 21 | PulseAudioException::~PulseAudioException() {} 22 | 23 | #endif 24 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/PulseAudioException.h: -------------------------------------------------------------------------------- 1 | #ifndef UTILS_PULSE_AUDIO_EXCEPTION_H 2 | #define UTILS_PULSE_AUDIO_EXCEPTION_H 3 | 4 | #if defined(__unix__) || defined(__linux__) 5 | 6 | #include 7 | 8 | #define THROW_PULSE_AUDIO_EXCEPTION(message, errorCode, errorDescription) \ 9 | throw introlab::PulseAudioException( \ 10 | __FILENAME__, \ 11 | __LOGGED_FUNCTION__, \ 12 | __LINE__, \ 13 | (message), \ 14 | (errorCode), \ 15 | (errorDescription)) 16 | 17 | namespace introlab 18 | { 19 | class PulseAudioException : public std::runtime_error 20 | { 21 | public: 22 | PulseAudioException( 23 | const std::string& filename, 24 | const std::string& function, 25 | int line, 26 | const std::string& message, 27 | int errorCode, 28 | const std::string& errorDescription); 29 | 30 | ~PulseAudioException() override; 31 | }; 32 | } 33 | 34 | #else 35 | 36 | #error "Invalid include file" 37 | 38 | #endif 39 | 40 | #endif 41 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/Semaphore.cpp: -------------------------------------------------------------------------------- 1 | #include "Semaphore.h" 2 | 3 | Semaphore::Semaphore(int count) : m_count(count) {} 4 | -------------------------------------------------------------------------------- /audio_utils/src/Utils/Semaphore.h: -------------------------------------------------------------------------------- 1 | #ifndef UTILS_SEMAPHORE_H 2 | #define UTILS_SEMAPHORE_H 3 | 4 | #include 5 | #include 6 | 7 | class Semaphore 8 | { 9 | int m_count; 10 | std::mutex m_mutex; 11 | std::condition_variable m_conditionVariable; 12 | 13 | public: 14 | Semaphore(int count); 15 | 16 | void release(); 17 | void acquire(); 18 | bool tryAcquire(); 19 | template 20 | bool tryAcquireFor(const std::chrono::duration& duration); 21 | }; 22 | 23 | inline void Semaphore::release() 24 | { 25 | std::lock_guard lock(m_mutex); 26 | m_count++; 27 | m_conditionVariable.notify_one(); 28 | } 29 | 30 | inline void Semaphore::acquire() 31 | { 32 | std::unique_lock lock(m_mutex); 33 | m_conditionVariable.wait(lock, [this]() { return m_count > 0; }); 34 | m_count--; 35 | } 36 | 37 | inline bool Semaphore::tryAcquire() 38 | { 39 | std::lock_guard lock(m_mutex); 40 | if (m_count > 0) 41 | { 42 | m_count--; 43 | return true; 44 | } 45 | else 46 | { 47 | return false; 48 | } 49 | } 50 | 51 | template 52 | inline bool Semaphore::tryAcquireFor(const std::chrono::duration& duration) 53 | { 54 | std::unique_lock lock(m_mutex); 55 | if (m_conditionVariable.wait_for(lock, duration, [this]() { return m_count > 0; })) 56 | { 57 | m_count--; 58 | return true; 59 | } 60 | else 61 | { 62 | return false; 63 | } 64 | } 65 | 66 | #endif 67 | -------------------------------------------------------------------------------- /audio_utils/src/beat_detector_node.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | #include 6 | 7 | #include 8 | 9 | #include 10 | 11 | using namespace introlab; 12 | 13 | constexpr size_t SupportedChannelCount = 1; 14 | 15 | class BeatDetectorNode : public rclcpp::Node 16 | { 17 | rclcpp::Subscription::SharedPtr m_audioSub; 18 | 19 | rclcpp::Publisher::SharedPtr m_bpmPub; 20 | rclcpp::Publisher::SharedPtr m_beatPub; 21 | 22 | std_msgs::msg::Float32 m_bpmMsg; 23 | std_msgs::msg::Bool m_beatMsg; 24 | 25 | size_t m_samplingFrequency; 26 | size_t m_frameSampleCount; 27 | 28 | std::unique_ptr m_musicBeatDetector; 29 | 30 | public: 31 | BeatDetectorNode() : rclcpp::Node("beat_detector_node") 32 | { 33 | m_samplingFrequency = declare_parameter("sampling_frequency", 44100); 34 | m_frameSampleCount = declare_parameter("frame_sample_count", 128); 35 | size_t ossFftWindowSize = declare_parameter("oss_fft_window_size", 1024); 36 | size_t fluxHammingSize = declare_parameter("flux_hamming_size", 15); 37 | size_t ossBpmWindowSize = declare_parameter("oss_bpm_window_size", 1024); 38 | float minBpm = declare_parameter("min_bpm", 50.f); 39 | float maxBpm = declare_parameter("max_bpm", 180.f); 40 | size_t bpmCandidateCount = declare_parameter("bpm_candidate_count", 10); 41 | 42 | m_musicBeatDetector = std::make_unique( 43 | m_samplingFrequency, 44 | m_frameSampleCount, 45 | ossFftWindowSize, 46 | fluxHammingSize, 47 | ossBpmWindowSize, 48 | minBpm, 49 | maxBpm, 50 | bpmCandidateCount); 51 | 52 | m_audioSub = create_subscription( 53 | "audio_in", 54 | 10, 55 | [this](const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) { audioCallback(msg); }); 56 | 57 | m_bpmPub = create_publisher("bpm", 1000); 58 | m_beatPub = create_publisher("beat", 1000); 59 | } 60 | 61 | void run() { rclcpp::spin(shared_from_this()); } 62 | 63 | private: 64 | void audioCallback(const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) 65 | { 66 | PcmAudioFrameFormat format = parseFormat(msg->format); 67 | if (msg->channel_count != SupportedChannelCount || msg->sampling_frequency != m_samplingFrequency || 68 | (msg->frame_sample_count % m_frameSampleCount) != 0 || 69 | msg->data.size() != size(format, msg->channel_count, msg->frame_sample_count)) 70 | { 71 | RCLCPP_ERROR( 72 | get_logger(), 73 | "Not supported audio frame (msg->channel_count=%d, " 74 | "sampling_frequency=%d, frame_sample_count=%d, data_size=%ld)", 75 | msg->channel_count, 76 | msg->sampling_frequency, 77 | msg->frame_sample_count, 78 | msg->data.size()); 79 | return; 80 | } 81 | 82 | PcmAudioFrame frame(format, msg->channel_count, msg->frame_sample_count, msg->data.data()); 83 | 84 | m_beatMsg.data = false; 85 | for (size_t i = 0; i < msg->frame_sample_count; i += m_frameSampleCount) 86 | { 87 | Beat beat = m_musicBeatDetector->detect(frame.slice(i, m_frameSampleCount)); 88 | m_bpmMsg.data = beat.bpm; 89 | m_beatMsg.data = m_beatMsg.data || beat.isBeat; 90 | } 91 | 92 | m_bpmPub->publish(m_bpmMsg); 93 | m_beatPub->publish(m_beatMsg); 94 | } 95 | }; 96 | 97 | int main(int argc, char** argv) 98 | { 99 | rclcpp::init(argc, argv); 100 | auto node = std::make_shared(); 101 | node->run(); 102 | rclcpp::shutdown(); 103 | 104 | return 0; 105 | } 106 | -------------------------------------------------------------------------------- /audio_utils/src/capture_node.cpp: -------------------------------------------------------------------------------- 1 | #include "PcmDevices/AlsaPcmDevice.h" 2 | #include "PcmDevices/PulseAudioPcmDevice.h" 3 | 4 | #include 5 | 6 | #include 7 | 8 | #include 9 | 10 | using namespace introlab; 11 | 12 | struct CaptureNodeConfiguration 13 | { 14 | PcmDevice::Backend backend; 15 | std::string backendString; 16 | std::string device; 17 | std::string formatString; 18 | PcmAudioFrameFormat format; 19 | int channelCount; 20 | int samplingFrequency; 21 | int frameSampleCount; 22 | int latencyUs; 23 | 24 | std::vector channelMap; 25 | 26 | bool merge; 27 | float gain; 28 | 29 | size_t queueSize; 30 | 31 | CaptureNodeConfiguration() 32 | : backend(PcmDevice::Backend::Alsa), 33 | format(PcmAudioFrameFormat::Signed8), 34 | channelCount(0), 35 | samplingFrequency(0), 36 | frameSampleCount(0), 37 | latencyUs(0), 38 | merge(false), 39 | gain(1.f) 40 | { 41 | } 42 | }; 43 | 44 | class AudioFrameTimestampCalculator 45 | { 46 | std::shared_ptr m_node; 47 | rclcpp::Clock m_clock; 48 | 49 | uint64_t m_samplingFrequency; 50 | uint64_t m_frameSampleCount; 51 | 52 | rclcpp::Duration m_tolerance; 53 | rclcpp::Duration m_minusTolerance; 54 | 55 | rclcpp::Time m_startTime; 56 | uint64_t m_sampleCount; 57 | 58 | public: 59 | AudioFrameTimestampCalculator(std::shared_ptr node, int samplingFrequency, int frameSampleCount) 60 | : m_node(std::move(node)), 61 | m_samplingFrequency(samplingFrequency), 62 | m_frameSampleCount(frameSampleCount), 63 | m_tolerance(std::chrono::milliseconds(500)), 64 | m_minusTolerance(std::chrono::milliseconds(-500)), 65 | m_startTime(m_clock.now()), 66 | m_sampleCount(0) 67 | { 68 | } 69 | 70 | rclcpp::Time next() 71 | { 72 | m_sampleCount += m_frameSampleCount; 73 | rclcpp::Time timestamp = m_startTime + sampleCountToDuration(m_samplingFrequency, m_sampleCount); 74 | resetIfOutOfTolerance(timestamp); 75 | 76 | return timestamp; 77 | } 78 | 79 | private: 80 | void resetIfOutOfTolerance(rclcpp::Time& timestamp) 81 | { 82 | rclcpp::Time now = m_clock.now(); 83 | rclcpp::Duration difference = now - timestamp; 84 | 85 | if (difference > m_tolerance || difference < m_minusTolerance) 86 | { 87 | timestamp = now; 88 | m_startTime = now; 89 | m_sampleCount = 0; 90 | RCLCPP_WARN(m_node->get_logger(), "The audio frame timestamp calculator has been reset."); 91 | } 92 | } 93 | 94 | static rclcpp::Duration sampleCountToDuration(uint64_t samplingFrequency, uint64_t sampleCount) 95 | { 96 | constexpr uint64_t NsecsPerSec = 1'000'000'000; 97 | uint32_t sec = sampleCount / samplingFrequency; 98 | uint32_t nsec = (sampleCount % samplingFrequency) * NsecsPerSec / samplingFrequency; 99 | 100 | return rclcpp::Duration(static_cast(sec), static_cast(nsec)); 101 | } 102 | }; 103 | 104 | void mergeChannels( 105 | const PcmAudioFrame& pcmInput, 106 | PcmAudioFrame& pcmOutput, 107 | PackedAudioFrame& input, 108 | PackedAudioFrame& output, 109 | float gain) 110 | { 111 | pcmInput.copyTo(input); 112 | if (output.channelCount() != 1 || output.sampleCount() != input.sampleCount()) 113 | { 114 | output = PackedAudioFrame(1, input.sampleCount()); 115 | } 116 | 117 | for (size_t sample = 0; sample < input.sampleCount(); sample++) 118 | { 119 | output[sample] = 0; 120 | for (size_t channel = 0; channel < input.channelCount(); channel++) 121 | { 122 | output[sample] += input[channel * input.sampleCount() + sample]; 123 | } 124 | 125 | output[sample] /= input.channelCount(); 126 | output[sample] *= gain; 127 | } 128 | 129 | pcmOutput = output; 130 | } 131 | 132 | void applyGain(PcmAudioFrame& pcmFrame, PackedAudioFrame& frame, float gain) 133 | { 134 | if (gain == 1.f) 135 | { 136 | return; 137 | } 138 | 139 | pcmFrame.copyTo(frame); 140 | for (size_t i = 0; i < frame.size(); i++) 141 | { 142 | frame[i] *= gain; 143 | } 144 | pcmFrame = frame; 145 | } 146 | 147 | std::unique_ptr createCaptureDevice(const CaptureNodeConfiguration& configuration) 148 | { 149 | switch (configuration.backend) 150 | { 151 | case PcmDevice::Backend::Alsa: 152 | return std::make_unique( 153 | configuration.device, 154 | PcmDevice::Stream::Capture, 155 | configuration.format, 156 | configuration.channelCount, 157 | configuration.frameSampleCount, 158 | configuration.samplingFrequency, 159 | configuration.latencyUs); 160 | case PcmDevice::Backend::PulseAudio: 161 | return std::make_unique( 162 | configuration.device, 163 | PcmDevice::Stream::Capture, 164 | configuration.format, 165 | configuration.channelCount, 166 | configuration.frameSampleCount, 167 | configuration.samplingFrequency, 168 | configuration.latencyUs, 169 | configuration.channelMap); 170 | default: 171 | THROW_INVALID_VALUE_EXCEPTION("backend", ""); 172 | } 173 | } 174 | 175 | void run( 176 | std::shared_ptr& node, 177 | std::unique_ptr captureDevice, 178 | const CaptureNodeConfiguration& configuration) 179 | { 180 | auto audioPub = node->create_publisher("audio_out", configuration.queueSize); 181 | 182 | PcmAudioFrame manyChannelPcmFrame(configuration.format, configuration.channelCount, configuration.frameSampleCount); 183 | PcmAudioFrame oneChannelPcmFrame(configuration.format, 1, configuration.frameSampleCount); 184 | PackedAudioFrame manyChannelFrame(configuration.channelCount, configuration.frameSampleCount); 185 | PackedAudioFrame oneChannelFrame(1, configuration.frameSampleCount); 186 | 187 | audio_utils_msgs::msg::AudioFrame audioFrameMsg; 188 | audioFrameMsg.format = configuration.formatString; 189 | audioFrameMsg.channel_count = configuration.merge ? 1 : configuration.channelCount; 190 | audioFrameMsg.sampling_frequency = configuration.samplingFrequency; 191 | audioFrameMsg.frame_sample_count = configuration.frameSampleCount; 192 | audioFrameMsg.data.resize(configuration.merge ? oneChannelPcmFrame.size() : manyChannelPcmFrame.size()); 193 | 194 | AudioFrameTimestampCalculator timestampCalculator( 195 | node, 196 | configuration.samplingFrequency, 197 | configuration.frameSampleCount); 198 | 199 | while (rclcpp::ok()) 200 | { 201 | captureDevice->read(manyChannelPcmFrame); 202 | 203 | if (configuration.merge) 204 | { 205 | mergeChannels( 206 | manyChannelPcmFrame, 207 | oneChannelPcmFrame, 208 | manyChannelFrame, 209 | oneChannelFrame, 210 | configuration.gain); 211 | memcpy(audioFrameMsg.data.data(), oneChannelPcmFrame.data(), audioFrameMsg.data.size()); 212 | } 213 | else 214 | { 215 | applyGain(manyChannelPcmFrame, manyChannelFrame, configuration.gain); 216 | memcpy(audioFrameMsg.data.data(), manyChannelPcmFrame.data(), audioFrameMsg.data.size()); 217 | } 218 | 219 | audioFrameMsg.header.stamp = timestampCalculator.next(); 220 | audioPub->publish(audioFrameMsg); 221 | 222 | rclcpp::spin_some(node); 223 | } 224 | } 225 | 226 | int main(int argc, char** argv) 227 | { 228 | rclcpp::init(argc, argv); 229 | 230 | auto node = rclcpp::Node::make_shared("capture_node"); 231 | 232 | CaptureNodeConfiguration configuration; 233 | configuration.backendString = node->declare_parameter("backend", "alsa"); 234 | 235 | try 236 | { 237 | configuration.backend = PcmDevice::parseBackend(configuration.backendString); 238 | 239 | configuration.device = node->declare_parameter("device", "default"); 240 | configuration.formatString = node->declare_parameter("format", "signed_16"); 241 | configuration.format = parseFormat(configuration.formatString); 242 | configuration.channelCount = node->declare_parameter("channel_count", 1); 243 | configuration.samplingFrequency = node->declare_parameter("sampling_frequency", 16000); 244 | configuration.frameSampleCount = node->declare_parameter("frame_sample_count", 1024); 245 | configuration.latencyUs = node->declare_parameter("latency_us", 64000); 246 | configuration.channelMap = node->declare_parameter("channel_map", std::vector{}); 247 | if (!configuration.channelMap.empty() && configuration.backend != PcmDevice::Backend::PulseAudio) 248 | { 249 | RCLCPP_WARN(node->get_logger(), "The parameter channel_map is only supported with the PulseAudio backend"); 250 | } 251 | 252 | configuration.merge = node->declare_parameter("merge", false); 253 | configuration.gain = node->declare_parameter("gain", 1.f); 254 | 255 | configuration.queueSize = node->declare_parameter("queue_size", 1); 256 | 257 | run(node, createCaptureDevice(configuration), configuration); 258 | } 259 | catch (const std::exception& e) 260 | { 261 | RCLCPP_ERROR(node->get_logger(), "%s", e.what()); 262 | return -1; 263 | } 264 | 265 | rclcpp::shutdown(); 266 | 267 | return 0; 268 | } 269 | -------------------------------------------------------------------------------- /audio_utils/src/playback_node.cpp: -------------------------------------------------------------------------------- 1 | #include "PcmDevices/AlsaPcmDevice.h" 2 | #include "PcmDevices/PulseAudioPcmDevice.h" 3 | #include "Utils/Semaphore.h" 4 | 5 | #include 6 | 7 | #include 8 | 9 | #include 10 | 11 | #include 12 | #include 13 | #include 14 | 15 | constexpr const char* NODE_NAME = "playback_node"; 16 | 17 | using namespace introlab; 18 | 19 | class PlaybackNode : public rclcpp::Node 20 | { 21 | PcmDevice::Backend m_backend; 22 | std::string m_device; 23 | std::string m_formatString; 24 | PcmAudioFrameFormat m_format; 25 | size_t m_channelCount; 26 | size_t m_samplingFrequency; 27 | size_t m_frameSampleCount; 28 | size_t m_latencyUs; 29 | std::vector m_channelMap; 30 | 31 | std::unique_ptr m_playbackDevice; 32 | std::unique_ptr m_emptyFrame; 33 | 34 | audio_utils_msgs::msg::AudioFrame::SharedPtr m_pendingFrame; 35 | Semaphore m_pendingFrameWriteSemaphore; 36 | Semaphore m_pendingFrameReadSemaphore; 37 | std::atomic> m_lastAudioFrameTime; 38 | std::chrono::nanoseconds m_frameDuration; 39 | 40 | rclcpp::Subscription::SharedPtr m_audioSub; 41 | 42 | public: 43 | explicit PlaybackNode() 44 | : rclcpp::Node(NODE_NAME), 45 | m_pendingFrameWriteSemaphore(1), 46 | m_pendingFrameReadSemaphore(0), 47 | m_lastAudioFrameTime(std::chrono::system_clock::now()) 48 | { 49 | m_backend = PcmDevice::parseBackend(declare_parameter("backend", "alsa")); 50 | m_device = declare_parameter("device", "default"); 51 | m_formatString = declare_parameter("format", "signed_16"); 52 | m_format = parseFormat(m_formatString); 53 | m_channelCount = declare_parameter("channel_count", 1); 54 | m_samplingFrequency = declare_parameter("sampling_frequency", 16000); 55 | m_frameSampleCount = declare_parameter("frame_sample_count", 1024); 56 | m_latencyUs = declare_parameter("latency_us", 64000); 57 | m_channelMap = declare_parameter("channel_map", std::vector{}); 58 | if (!m_channelMap.empty() && m_backend != PcmDevice::Backend::PulseAudio) 59 | { 60 | RCLCPP_WARN(get_logger(), "The parameter channel_map is only supported with the PulseAudio backend"); 61 | } 62 | 63 | size_t queueSize = declare_parameter("queue_size", 1); 64 | 65 | m_frameDuration = std::chrono::milliseconds(1000 * m_frameSampleCount / m_samplingFrequency); 66 | 67 | m_playbackDevice = createPlaybackDevice(); 68 | m_emptyFrame = std::make_unique(m_format, m_channelCount, m_frameSampleCount); 69 | m_emptyFrame->clear(); 70 | 71 | m_audioSub = create_subscription( 72 | "audio_in", 73 | queueSize, 74 | [this](const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) { audioCallback(msg); }); 75 | } 76 | 77 | void run() 78 | { 79 | std::thread spinThread([this]() { rclcpp::spin(shared_from_this()); }); 80 | 81 | while (rclcpp::ok()) 82 | { 83 | writeStep(); 84 | } 85 | 86 | m_pendingFrameWriteSemaphore.release(); 87 | spinThread.join(); 88 | } 89 | 90 | private: 91 | void audioCallback(const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) 92 | { 93 | if (msg->format != m_formatString || msg->channel_count != m_channelCount || 94 | msg->sampling_frequency != m_samplingFrequency || msg->frame_sample_count != m_frameSampleCount || 95 | msg->data.size() != size(m_format, msg->channel_count, msg->frame_sample_count)) 96 | { 97 | RCLCPP_ERROR( 98 | get_logger(), 99 | "Not supported audio frame (msg->format=%s, msg->channel_count=%d," 100 | "sampling_frequency=%d, frame_sample_count=%d, data_size=%ld)", 101 | msg->format.c_str(), 102 | msg->channel_count, 103 | msg->sampling_frequency, 104 | msg->frame_sample_count, 105 | msg->data.size()); 106 | return; 107 | } 108 | 109 | m_pendingFrameWriteSemaphore.acquire(); 110 | m_pendingFrame = msg; 111 | m_lastAudioFrameTime.store(std::chrono::system_clock::now()); 112 | m_pendingFrameReadSemaphore.release(); 113 | } 114 | 115 | void writeStep() 116 | { 117 | m_playbackDevice->wait(); 118 | 119 | if (m_pendingFrameReadSemaphore.tryAcquireFor(m_frameDuration / 2)) 120 | { 121 | PcmAudioFrame frame(m_format, m_channelCount, m_frameSampleCount, m_pendingFrame->data.data()); 122 | m_playbackDevice->write(frame); 123 | m_pendingFrameWriteSemaphore.release(); 124 | } 125 | else if ((std::chrono::system_clock::now() - m_lastAudioFrameTime.load()) > 2 * m_frameDuration) 126 | { 127 | m_playbackDevice->write(*m_emptyFrame); 128 | } 129 | } 130 | 131 | std::unique_ptr createPlaybackDevice() 132 | { 133 | switch (m_backend) 134 | { 135 | case PcmDevice::Backend::Alsa: 136 | return std::make_unique( 137 | m_device, 138 | PcmDevice::Stream::Playback, 139 | m_format, 140 | m_channelCount, 141 | m_frameSampleCount, 142 | m_samplingFrequency, 143 | m_latencyUs); 144 | case PcmDevice::Backend::PulseAudio: 145 | return std::make_unique( 146 | m_device, 147 | PcmDevice::Stream::Playback, 148 | m_format, 149 | m_channelCount, 150 | m_frameSampleCount, 151 | m_samplingFrequency, 152 | m_latencyUs, 153 | m_channelMap); 154 | default: 155 | THROW_INVALID_VALUE_EXCEPTION("backend", ""); 156 | } 157 | } 158 | }; 159 | 160 | int main(int argc, char** argv) 161 | { 162 | rclcpp::init(argc, argv); 163 | 164 | try 165 | { 166 | auto node = std::make_shared(); 167 | node->run(); 168 | } 169 | catch (const std::exception& e) 170 | { 171 | RCLCPP_ERROR(rclcpp::get_logger(NODE_NAME), "%s", e.what()); 172 | return -1; 173 | } 174 | 175 | rclcpp::shutdown(); 176 | 177 | return 0; 178 | } 179 | -------------------------------------------------------------------------------- /audio_utils/src/vad_node.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | #include 5 | 6 | #include 7 | #include 8 | 9 | #include 10 | #include 11 | 12 | #include 13 | 14 | #include 15 | 16 | using namespace introlab; 17 | using namespace std; 18 | 19 | constexpr size_t SupportedChannelCount = 1; 20 | constexpr size_t SupportedSamplingFrequency = 16000; 21 | constexpr size_t SupportedFrameSampleCount = 512; 22 | 23 | constexpr const char* NODE_NAME = "vad_node"; 24 | 25 | enum class VadStateType 26 | { 27 | SILENCE, 28 | VOICE, 29 | SILENCE_PENDING 30 | }; 31 | 32 | // Inspired by https://github.com/snakers4/silero-vad/blob/master/examples/cpp/silero-vad-onnx.cpp 33 | class Vad 34 | { 35 | static constexpr size_t SIZE_HC = 128; 36 | 37 | float m_silenceToVoiceThreshold; 38 | float m_voiceToSilenceThreshold; 39 | size_t m_minSilenceFrameCount; 40 | 41 | PackedAudioFrame m_packedAudioFrame; 42 | 43 | Ort::Env m_env; 44 | Ort::SessionOptions m_sessionOptions; 45 | unique_ptr m_session; 46 | Ort::MemoryInfo m_cpuMemoryInfo; 47 | 48 | vector m_ortInputsNames; 49 | vector m_ortInputs; 50 | 51 | vector m_inputShape; 52 | 53 | vector m_sr; 54 | vector m_srShape; 55 | 56 | vector m_h; 57 | vector m_c; 58 | vector m_hcShape; 59 | 60 | vector m_ortOutputsNames; 61 | 62 | // State 63 | VadStateType m_stateType; 64 | size_t m_frameIndex; 65 | size_t m_silenceFrameIndex; 66 | 67 | public: 68 | Vad(float silenceToVoiceThreshold, float voiceToSilenceThreshold, size_t minSilenceFrameCount) 69 | : m_silenceToVoiceThreshold(silenceToVoiceThreshold), 70 | m_voiceToSilenceThreshold(voiceToSilenceThreshold), 71 | m_minSilenceFrameCount(minSilenceFrameCount), 72 | m_packedAudioFrame(1, SupportedFrameSampleCount), 73 | m_cpuMemoryInfo(nullptr), 74 | m_ortInputsNames({"input", "sr", "h", "c"}), 75 | m_inputShape({1, SupportedFrameSampleCount}), 76 | m_sr({SupportedSamplingFrequency}), 77 | m_srShape({1}), 78 | m_h(SIZE_HC), 79 | m_c(SIZE_HC), 80 | m_hcShape({2, 1, 64}), 81 | m_ortOutputsNames({"output", "hn", "cn"}) 82 | { 83 | m_sessionOptions.SetInterOpNumThreads(1); 84 | m_sessionOptions.SetIntraOpNumThreads(1); 85 | m_sessionOptions.SetGraphOptimizationLevel(GraphOptimizationLevel::ORT_ENABLE_EXTENDED); 86 | m_sessionOptions.SetExecutionMode(ExecutionMode::ORT_SEQUENTIAL); 87 | m_sessionOptions.SetLogSeverityLevel(ORT_LOGGING_LEVEL_ERROR); 88 | 89 | string modelPath = ament_index_cpp::get_package_share_directory("audio_utils") + "/models/silero_vad.onnx"; 90 | m_session = make_unique(m_env, modelPath.c_str(), m_sessionOptions); 91 | m_cpuMemoryInfo = Ort::MemoryInfo::CreateCpu(OrtArenaAllocator, OrtMemTypeDefault); 92 | 93 | reset(); 94 | } 95 | 96 | DECLARE_NOT_COPYABLE(Vad); 97 | DECLARE_NOT_MOVABLE(Vad); 98 | 99 | void reset() 100 | { 101 | memset(m_h.data(), 0, m_h.size() * sizeof(float)); 102 | memset(m_c.data(), 0, m_c.size() * sizeof(float)); 103 | 104 | m_stateType = VadStateType::SILENCE; 105 | m_frameIndex = 0; 106 | m_silenceFrameIndex = 0; 107 | } 108 | 109 | bool detect(const PcmAudioFrame& pcmAudioframe) 110 | { 111 | if (pcmAudioframe.channelCount() != 1 || pcmAudioframe.sampleCount() != SupportedFrameSampleCount) 112 | { 113 | THROW_NOT_SUPPORTED_EXCEPTION("Invalid frame"); 114 | } 115 | 116 | m_packedAudioFrame = pcmAudioframe; 117 | m_ortInputs.clear(); 118 | m_ortInputs.emplace_back(Ort::Value::CreateTensor( 119 | m_cpuMemoryInfo, 120 | m_packedAudioFrame.data(), 121 | m_packedAudioFrame.size(), 122 | m_inputShape.data(), 123 | m_inputShape.size())); 124 | m_ortInputs.emplace_back(Ort::Value::CreateTensor( 125 | m_cpuMemoryInfo, 126 | m_sr.data(), 127 | m_sr.size(), 128 | m_srShape.data(), 129 | m_srShape.size())); 130 | m_ortInputs.emplace_back(Ort::Value::CreateTensor( 131 | m_cpuMemoryInfo, 132 | m_h.data(), 133 | m_h.size(), 134 | m_hcShape.data(), 135 | m_hcShape.size())); 136 | m_ortInputs.emplace_back(Ort::Value::CreateTensor( 137 | m_cpuMemoryInfo, 138 | m_c.data(), 139 | m_c.size(), 140 | m_hcShape.data(), 141 | m_hcShape.size())); 142 | 143 | vector ortOutputs = m_session->Run( 144 | Ort::RunOptions{nullptr}, 145 | m_ortInputsNames.data(), 146 | m_ortInputs.data(), 147 | m_ortInputs.size(), 148 | m_ortOutputsNames.data(), 149 | m_ortOutputsNames.size()); 150 | float voiceProbability = ortOutputs[0].GetTensorMutableData()[0]; 151 | float* hn = ortOutputs[1].GetTensorMutableData(); 152 | memcpy(m_h.data(), hn, m_h.size() * sizeof(float)); 153 | float* cn = ortOutputs[2].GetTensorMutableData(); 154 | memcpy(m_c.data(), cn, m_c.size() * sizeof(float)); 155 | 156 | return updateState(voiceProbability); 157 | } 158 | 159 | bool updateState(float voiceProbability) 160 | { 161 | m_frameIndex++; 162 | 163 | if (m_stateType == VadStateType::SILENCE && voiceProbability > m_silenceToVoiceThreshold) 164 | { 165 | m_stateType = VadStateType::VOICE; 166 | } 167 | else if (m_stateType == VadStateType::VOICE && voiceProbability < m_voiceToSilenceThreshold) 168 | { 169 | m_stateType = VadStateType::SILENCE_PENDING; 170 | m_silenceFrameIndex = m_frameIndex; 171 | } 172 | else if (m_stateType == VadStateType::SILENCE_PENDING && voiceProbability > m_voiceToSilenceThreshold) 173 | { 174 | m_stateType = VadStateType::VOICE; 175 | } 176 | else if ( 177 | m_stateType == VadStateType::SILENCE_PENDING && 178 | (m_frameIndex - m_silenceFrameIndex) > m_minSilenceFrameCount) 179 | { 180 | m_stateType = VadStateType::SILENCE; 181 | } 182 | 183 | switch (m_stateType) 184 | { 185 | case VadStateType::SILENCE: 186 | return false; 187 | case VadStateType::VOICE: 188 | case VadStateType::SILENCE_PENDING: 189 | return true; 190 | default: 191 | return false; 192 | } 193 | } 194 | }; 195 | 196 | class VadNode : public rclcpp::Node 197 | { 198 | rclcpp::Subscription::SharedPtr m_audioSub; 199 | rclcpp::Publisher::SharedPtr m_voiceActivityPub; 200 | 201 | Vad m_vad; 202 | audio_utils_msgs::msg::VoiceActivity m_voiceActivityMsg; 203 | 204 | public: 205 | VadNode() 206 | : rclcpp::Node(NODE_NAME), 207 | m_vad( 208 | declare_parameter("silence_to_voice_threshold", 0.5f), 209 | declare_parameter("voice_to_silence_threshold", 0.4f), 210 | declare_parameter("min_silence_duration_ms", 500) * SupportedSamplingFrequency / 1000 / 211 | SupportedFrameSampleCount) 212 | { 213 | m_audioSub = create_subscription( 214 | "audio_in", 215 | 100, 216 | [this](const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) { audioCallback(msg); }); 217 | m_voiceActivityPub = create_publisher("voice_activity", 100); 218 | } 219 | 220 | void run() { rclcpp::spin(shared_from_this()); } 221 | 222 | private: 223 | void audioCallback(const audio_utils_msgs::msg::AudioFrame::SharedPtr msg) 224 | { 225 | PcmAudioFrameFormat format = parseFormat(msg->format); 226 | if (msg->channel_count != SupportedChannelCount || msg->sampling_frequency != SupportedSamplingFrequency || 227 | (msg->frame_sample_count % SupportedFrameSampleCount) != 0 || 228 | msg->data.size() != size(format, msg->channel_count, msg->frame_sample_count)) 229 | { 230 | RCLCPP_ERROR( 231 | get_logger(), 232 | "Not supported audio frame (msg->channel_count=%d, " 233 | "sampling_frequency=%d, frame_sample_count=%d, data_size=%ld)", 234 | msg->channel_count, 235 | msg->sampling_frequency, 236 | msg->frame_sample_count, 237 | msg->data.size()); 238 | return; 239 | } 240 | 241 | PcmAudioFrame frame(format, msg->channel_count, msg->frame_sample_count, msg->data.data()); 242 | 243 | m_voiceActivityMsg.header = msg->header; 244 | m_voiceActivityMsg.is_voice = false; 245 | for (size_t i = 0; i < msg->frame_sample_count; i += SupportedFrameSampleCount) 246 | { 247 | m_voiceActivityMsg.is_voice = 248 | m_voiceActivityMsg.is_voice || m_vad.detect(frame.slice(i, SupportedFrameSampleCount)); 249 | } 250 | 251 | m_voiceActivityPub->publish(m_voiceActivityMsg); 252 | } 253 | }; 254 | 255 | int main(int argc, char** argv) 256 | { 257 | rclcpp::init(argc, argv); 258 | try 259 | { 260 | auto node = std::make_shared(); 261 | node->run(); 262 | } 263 | catch (const exception& e) 264 | { 265 | RCLCPP_ERROR(rclcpp::get_logger(NODE_NAME), "%s", e.what()); 266 | return -1; 267 | } 268 | rclcpp::shutdown(); 269 | return 0; 270 | } 271 | -------------------------------------------------------------------------------- /audio_utils_msgs/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | cmake_minimum_required(VERSION 3.5) 2 | project(audio_utils_msgs) 3 | 4 | # Default to C99 5 | if(NOT CMAKE_C_STANDARD) 6 | set(CMAKE_C_STANDARD 99) 7 | endif() 8 | 9 | # Default to C++17 10 | if(NOT CMAKE_CXX_STANDARD) 11 | set(CMAKE_CXX_STANDARD 17) 12 | endif() 13 | 14 | if(CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang") 15 | add_compile_options(-Wall -Wextra -Wpedantic) 16 | endif() 17 | 18 | # Find dependencies 19 | find_package(ament_cmake REQUIRED) 20 | find_package(std_msgs REQUIRED) 21 | find_package(rosidl_default_generators REQUIRED) 22 | 23 | # Generate messages 24 | rosidl_generate_interfaces(${PROJECT_NAME} 25 | "msg/AudioFrame.msg" 26 | "msg/VoiceActivity.msg" 27 | DEPENDENCIES std_msgs 28 | ) 29 | 30 | ament_export_dependencies(std_msgs) 31 | 32 | ament_package() 33 | -------------------------------------------------------------------------------- /audio_utils_msgs/msg/AudioFrame.msg: -------------------------------------------------------------------------------- 1 | std_msgs/Header header 2 | 3 | # Supported formats (all formats are little endian): 4 | # - "signed_8" 5 | # - "signed_16" 6 | # - "signed_24" 7 | # - "signed_padded_24" 8 | # - "signed_32" 9 | # - "unsigned_8" 10 | # - "unsigned_16" 11 | # - "unsigned_24" 12 | # - "unsigned_padded_24" 13 | # - "unsigned_32" 14 | # - "float" 15 | # - "double" 16 | string format 17 | uint32 channel_count 18 | uint32 sampling_frequency 19 | uint32 frame_sample_count 20 | 21 | uint8[] data 22 | -------------------------------------------------------------------------------- /audio_utils_msgs/msg/VoiceActivity.msg: -------------------------------------------------------------------------------- 1 | std_msgs/Header header 2 | bool is_voice 3 | -------------------------------------------------------------------------------- /audio_utils_msgs/package.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | audio_utils_msgs 5 | 0.0.0 6 | The audio_utils_msgs package 7 | Marc-Antoine Maheux 8 | GPL-3.0 license 9 | 10 | ament_cmake 11 | rosidl_default_generators 12 | 13 | std_msgs 14 | 15 | rosidl_default_runtime 16 | ros2launch 17 | rosidl_interface_packages 18 | 19 | ament_lint_auto 20 | ament_lint_common 21 | 22 | 23 | ament_cmake 24 | 25 | 26 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | numpy 2 | scipy 3 | --------------------------------------------------------------------------------