├── .gitignore ├── LICENSE ├── README.md ├── features.py ├── interface.py ├── requirements.txt ├── skgmm.py ├── speaker-recognition.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | .*.swp 2 | *.pyc 3 | *.out 4 | *.wav 5 | venv/ 6 | .env 7 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2018 Xy Chen 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ### About 2 | This project is a simple python3 version of [speaker-recognition](https://github.com/ppwwyyxx/speaker-recognition) and I make a little change for the convenience of command line usage. 3 | 4 | ### difference with speaker-recognition of python2 5 | + Neither use MFCC implementation of bob nor implement that myself. Use the [python_speech_features](https://github.com/jameslyons/python_speech_features) instead. 6 | + Remove the GUI and you can only use the command line to train and predict the model. 7 | + Replace the function and class in sklearn which will be removed in the later version. 8 | + Use softmax function to output the probability. 9 | + convert to mono if the origin audio if stereo. 10 | 11 | ### Usage 12 | ```sh 13 | usage: speaker-recognition.py [-h] -t TASK -i INPUT -m MODEL 14 | 15 | Speaker Recognition Command Line Tool 16 | 17 | optional arguments: 18 | -h, --help show this help message and exit 19 | -t TASK, --task TASK Task to do. Either "enroll" or "predict" 20 | -i INPUT, --input INPUT 21 | Input Files(to predict) or Directories(to enroll) 22 | -m MODEL, --model MODEL 23 | Model file to save(in enroll) or use(in predict) 24 | 25 | Wav files in each input directory will be labeled as the basename of the directory. 26 | Note that wildcard inputs should be *quoted*, and they will be sent to glob module. 27 | 28 | Examples: 29 | Train: 30 | ./speaker-recognition.py -t enroll -i "/tmp/person* ./mary" -m model.out 31 | 32 | Predict: 33 | ./speaker-recognition.py -t predict -i "./*.wav" -m model.out 34 | ``` 35 | -------------------------------------------------------------------------------- /features.py: -------------------------------------------------------------------------------- 1 | from python_speech_features import mfcc 2 | import numpy as np 3 | 4 | def get_feature(fs, signal): 5 | mfcc_feature = mfcc(signal, fs) 6 | if len(mfcc_feature) == 0: 7 | print >> sys.stderr, "ERROR.. failed to extract mfcc feature:", len(signal) 8 | return mfcc_feature 9 | -------------------------------------------------------------------------------- /interface.py: -------------------------------------------------------------------------------- 1 | import pickle 2 | from collections import defaultdict 3 | from skgmm import GMMSet 4 | from features import get_feature 5 | import time 6 | 7 | class ModelInterface: 8 | 9 | def __init__(self): 10 | self.features = defaultdict(list) 11 | self.gmmset = GMMSet() 12 | 13 | def enroll(self, name, fs, signal): 14 | feat = get_feature(fs, signal) 15 | self.features[name].extend(feat) 16 | 17 | def train(self): 18 | self.gmmset = GMMSet() 19 | start_time = time.time() 20 | for name, feats in self.features.items(): 21 | try: 22 | self.gmmset.fit_new(feats, name) 23 | except Exception as e : 24 | print ("%s failed"%(name)) 25 | print (time.time() - start_time, " seconds") 26 | 27 | def dump(self, fname): 28 | """ dump all models to file""" 29 | self.gmmset.before_pickle() 30 | with open(fname, 'wb') as f: 31 | pickle.dump(self, f, -1) 32 | self.gmmset.after_pickle() 33 | 34 | def predict(self, fs, signal): 35 | """ 36 | return a label (name) 37 | """ 38 | try: 39 | feat = get_feature(fs, signal) 40 | except Exception as e: 41 | print (e) 42 | return self.gmmset.predict_one(feat) 43 | 44 | @staticmethod 45 | def load(fname): 46 | """ load from a dumped model file""" 47 | with open(fname, 'rb') as f: 48 | R = pickle.load(f) 49 | R.gmmset.after_pickle() 50 | return R 51 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | appnope==0.1.0 2 | decorator==4.0.10 3 | numpy==1.11.3 4 | pexpect==4.2.1 5 | pickleshare==0.7.4 6 | prompt-toolkit==1.0.9 7 | ptyprocess==0.5.1 8 | Pygments==2.1.3 9 | python-speech-features==0.4 10 | scikit-learn==0.18.1 11 | scipy==0.18.1 12 | simplegeneric==0.8.1 13 | six==1.10.0 14 | sklearn==0.0 15 | traitlets==4.3.1 16 | wcwidth==0.1.7 17 | -------------------------------------------------------------------------------- /skgmm.py: -------------------------------------------------------------------------------- 1 | from sklearn.mixture import GaussianMixture 2 | import operator 3 | import numpy as np 4 | import math 5 | 6 | class GMMSet: 7 | 8 | def __init__(self, gmm_order = 32): 9 | self.gmms = [] 10 | self.gmm_order = gmm_order 11 | self.y = [] 12 | 13 | def fit_new(self, x, label): 14 | self.y.append(label) 15 | gmm = GaussianMixture(self.gmm_order) 16 | gmm.fit(x) 17 | self.gmms.append(gmm) 18 | 19 | def gmm_score(self, gmm, x): 20 | return np.sum(gmm.score(x)) 21 | 22 | @staticmethod 23 | def softmax(scores): 24 | scores_sum = sum([math.exp(i) for i in scores]) 25 | score_max = math.exp(max(scores)) 26 | return round(score_max / scores_sum, 3) 27 | 28 | def predict_one(self, x): 29 | scores = [self.gmm_score(gmm, x) / len(x) for gmm in self.gmms] 30 | p = sorted(enumerate(scores), key=operator.itemgetter(1), reverse=True) 31 | p = [(str(self.y[i]), y, p[0][1] - y) for i, y in p] 32 | result = [(self.y[index], value) for (index, value) in enumerate(scores)] 33 | p = max(result, key=operator.itemgetter(1)) 34 | softmax_score = self.softmax(scores) 35 | return p[0], softmax_score 36 | 37 | def before_pickle(self): 38 | pass 39 | 40 | def after_pickle(self): 41 | pass 42 | -------------------------------------------------------------------------------- /speaker-recognition.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import os 4 | import sys 5 | import itertools 6 | import glob 7 | import argparse 8 | from utils import read_wav 9 | from interface import ModelInterface 10 | 11 | def get_args(): 12 | desc = "Speaker Recognition Command Line Tool" 13 | epilog = """ 14 | Wav files in each input directory will be labeled as the basename of the directory. 15 | Note that wildcard inputs should be *quoted*, and they will be sent to glob.glob module. 16 | Examples: 17 | Train (enroll a list of person named person*, and mary, with wav files under corresponding directories): 18 | ./speaker-recognition.py -t enroll -i "/tmp/person* ./mary" -m model.out 19 | Predict (predict the speaker of all wav files): 20 | ./speaker-recognition.py -t predict -i "./*.wav" -m model.out 21 | """ 22 | parser = argparse.ArgumentParser(description=desc,epilog=epilog, 23 | formatter_class=argparse.RawDescriptionHelpFormatter) 24 | 25 | parser.add_argument('-t', '--task', 26 | help='Task to do. Either "enroll" or "predict"', 27 | required=True) 28 | 29 | parser.add_argument('-i', '--input', 30 | help='Input Files(to predict) or Directories(to enroll)', 31 | required=True) 32 | 33 | parser.add_argument('-m', '--model', 34 | help='Model file to save(in enroll) or use(in predict)', 35 | required=True) 36 | 37 | ret = parser.parse_args() 38 | return ret 39 | 40 | def task_enroll(input_dirs, output_model): 41 | m = ModelInterface() 42 | input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()] 43 | dirs = itertools.chain(*(glob.glob(d) for d in input_dirs)) 44 | dirs = [d for d in dirs if os.path.isdir(d)] 45 | 46 | files = [] 47 | if len(dirs) == 0: 48 | print ("No valid directory found!") 49 | sys.exit(1) 50 | 51 | for d in dirs: 52 | label = os.path.basename(d.rstrip('/')) 53 | wavs = glob.glob(d + '/*.wav') 54 | 55 | if len(wavs) == 0: 56 | print ("No wav file found in %s"%(d)) 57 | continue 58 | for wav in wavs: 59 | try: 60 | fs, signal = read_wav(wav) 61 | m.enroll(label, fs, signal) 62 | print("wav %s has been enrolled"%(wav)) 63 | except Exception as e: 64 | print(wav + " error %s"%(e)) 65 | 66 | m.train() 67 | m.dump(output_model) 68 | 69 | def task_predict(input_files, input_model): 70 | m = ModelInterface.load(input_model) 71 | for f in glob.glob(os.path.expanduser(input_files)): 72 | fs, signal = read_wav(f) 73 | label, score = m.predict(fs, signal) 74 | print (f, '->', label, ", score->", score) 75 | 76 | if __name__ == "__main__": 77 | global args 78 | args = get_args() 79 | 80 | task = args.task 81 | if task == 'enroll': 82 | task_enroll(args.input, args.model) 83 | elif task == 'predict': 84 | task_predict(args.input, args.model) 85 | -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- 1 | from scipy.io import wavfile 2 | 3 | def read_wav(fname): 4 | fs, signal = wavfile.read(fname) 5 | if len(signal.shape) != 1: 6 | print("convert stereo to mono") 7 | signal = signal[:,0] 8 | return fs, signal 9 | --------------------------------------------------------------------------------