├── .gitignore ├── LICENSE ├── README.md ├── auorange ├── __init__.py ├── auorange.py ├── tests │ └── utils_test.py └── utils.py ├── figs ├── lpc.png └── mels.png ├── librosa_predict.py ├── requirements.txt └── wavs ├── LJ001-0001.wav ├── audio.wav ├── error.wav └── pred.wav /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | .vscode 3 | **/__pycache__ 4 | **/*.pyc 5 | -------------------------------------------------------------------------------- /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 | Copyright 2020-2025 Yablon Ding 179 | 180 | Licensed under the Apache License, Version 2.0 (the "License"); 181 | you may not use this file except in compliance with the License. 182 | You may obtain a copy of the License at 183 | 184 | http://www.apache.org/licenses/LICENSE-2.0 185 | 186 | Unless required by applicable law or agreed to in writing, software 187 | distributed under the License is distributed on an "AS IS" BASIS, 188 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 189 | See the License for the specific language governing permissions and 190 | limitations under the License. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Auorange: LPC prediction for audios using mel spectrogram 2 | 3 | This repo contains codes that calculate linear prediction from mel spectrogram. 4 | 5 | Can be used in Text to Speech vocoder like lpcnet or feather wave, etc. 6 | 7 | ## requirements 8 | 9 | python3.5 or higher 10 | 11 | ## Run 12 | 13 | Run this script to generate examples in wavs 14 | ``` 15 | python librosa_predict.py 16 | ``` 17 | 18 | ## Results 19 | 20 | Original audio is wavs/LJ001-0001.wav, which is the same as wavs/audio.wav. 21 | 22 | ### Librosa Feathre Extractor 23 | 24 | Mel spectrogram are extracted using librosa. 25 | 26 | Mel spectrogram is 27 | ![mels](./figs/mels.png) 28 | 29 | Predicted audio, original audio and error between two of them are 30 | 31 | ![audio](./figs/lpc.png) 32 | 33 | ## TODO: 34 | 35 | - [ ] Add More comments 36 | - [ ] Extract audio feature using tensorflow 37 | - [ ] Extract audio feature using pytorch 38 | -------------------------------------------------------------------------------- /auorange/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Yablon Ding 2 | 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | -------------------------------------------------------------------------------- /auorange/auorange.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Yablon Ding 2 | 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import math 15 | 16 | import librosa 17 | import numpy as np 18 | import scipy 19 | from scipy.fftpack import ifft 20 | from scipy.io import wavfile 21 | 22 | from auorange.utils import levinson_durbin 23 | 24 | 25 | def load_wav(path, sample_rate): 26 | sr, raw_data = wavfile.read(path) 27 | if sample_rate != sr: 28 | raise ValueError('sample rate not equal') 29 | raw_data = raw_data.astype(np.float32) 30 | return (raw_data + 32768) / 65535. * 2 - 1 31 | 32 | 33 | def save_wav(wav, path, sample_rate): 34 | data = (wav + 1) / 2 * 65535. - 32768 35 | wavfile.write(path, sample_rate, data.astype(np.int16)) 36 | 37 | 38 | class AudioLPC: 39 | 40 | def __init__(self, lpc_order, clip_lpc, sample_rate, f0=40.): 41 | self.lpc_order = lpc_order 42 | theta = (2 * np.pi * f0 / sample_rate)**2 43 | self.lag_window = np.exp( 44 | [[-0.5 * theta * i**2] for i in range(lpc_order + 1)]) 45 | self.clip_lpc = clip_lpc 46 | 47 | def autocorrelation_to_lpc(self, ac): 48 | ac = ac[0:self.lpc_order + 1, :] 49 | ac = ac * self.lag_window 50 | return levinson_durbin(self.lpc_order, ac) 51 | 52 | def linear_to_autocorrelation(self, linear): 53 | power = linear**2 54 | fft_power = np.concatenate([power, power[::-1, :][1:-1, :]], axis=0) 55 | return ifft(fft_power, n=fft_power.shape[0], axis=0).real 56 | 57 | def linear_to_lpc(self, linear, repeat=None): 58 | autocorrelation = self.linear_to_autocorrelation(linear) 59 | lpcs = self.autocorrelation_to_lpc(autocorrelation) 60 | lpcs = -1 * lpcs[::-1, :] 61 | if repeat is not None: 62 | return np.repeat(lpcs, repeat, axis=-1) 63 | return lpcs 64 | 65 | def predict(self, lpcs, signal_slice): 66 | pred = np.sum(lpcs * signal_slice, axis=0) 67 | if self.clip_lpc: 68 | pred = np.clip(pred, -1., 1.) 69 | return pred 70 | 71 | def reconstruct(self, lpcs, audio): 72 | num_points = lpcs.shape[-1] 73 | if audio.shape[0] == num_points: 74 | audio = np.pad(audio, ((self.lpc_order, 0)), 'constant') 75 | elif audio.shape[0] != num_points + self.lpc_order: 76 | raise RuntimeError('dimensions of lpcs and audio must match') 77 | indices = np.reshape(np.arange(self.lpc_order), [-1, 1]) + np.arange( 78 | lpcs.shape[-1]) 79 | signal_slices = audio[indices] 80 | pred = self.predict(lpcs, signal_slices) 81 | origin_audio = audio[self.lpc_order:] 82 | error = origin_audio - pred 83 | return origin_audio, pred, error 84 | 85 | 86 | class LibrosaAudioFeature: 87 | 88 | def __init__(self, sample_rate, n_fft, num_mels, hop_length, win_length, 89 | lpc_extractor): 90 | self.sample_rate = sample_rate 91 | self.n_fft = n_fft 92 | self.hop_length = hop_length 93 | self.win_length = win_length 94 | self.num_mels = num_mels 95 | self._mel_basis = librosa.filters.mel(self.sample_rate, 96 | self.n_fft, 97 | n_mels=self.num_mels, 98 | fmin=20., 99 | fmax=sample_rate / 2) 100 | self._inv_mel_basis = np.linalg.pinv(self._mel_basis) 101 | self.lpc_extractor = lpc_extractor 102 | 103 | def mel_spectrogram(self, y): 104 | D = self._stft(y) 105 | S = self._linear_to_mel(np.abs(D)) 106 | return normalize_spec(S) 107 | 108 | def linear_spectrogram(self, y): 109 | D = np.abs(self._stft(y)) 110 | return normalize_spec(D) 111 | 112 | def mel_to_linear(self, mel): 113 | mel = denormalize_spec(mel) 114 | return np.maximum(np.dot(self._inv_mel_basis, mel), 1e-12) 115 | 116 | def _linear_to_mel(self, spectrogram): 117 | return np.dot(self._mel_basis, spectrogram) 118 | 119 | def mel_to_lpc(self, mel): 120 | inv_linear = self.mel_to_linear(mel) 121 | return self.lpc_extractor.linear_to_lpc(inv_linear, repeat=self.hop_length) 122 | 123 | def lpc_audio(self, mel, audio): 124 | lpcs = self.mel_to_lpc(mel) 125 | lpcs = lpcs[:, :audio.shape[-1]] 126 | return self.lpc_extractor.reconstruct(lpcs, audio) 127 | 128 | def _stft(self, y): 129 | return librosa.stft(y=y, 130 | n_fft=self.n_fft, 131 | hop_length=self.hop_length, 132 | win_length=self.win_length, 133 | pad_mode='constant') 134 | 135 | def _istft(self, y): 136 | return librosa.istft(y, 137 | hop_length=self.hop_length, 138 | win_length=self.win_length) 139 | 140 | 141 | def normalize_spec(spectrogram): 142 | return np.log(1. + 10000 * spectrogram) 143 | 144 | 145 | def denormalize_spec(spectrogram): 146 | return (np.exp(spectrogram) - 1.) / 10000 147 | -------------------------------------------------------------------------------- /auorange/tests/utils_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | import numpy as np 3 | from auorange.utils import multiband_linear_spectrogram 4 | 5 | 6 | class TestMultibandLinear(unittest.TestCase): 7 | 8 | def testSplitFullBandLinear(self): 9 | fft_size = 16 10 | full_band_linear = np.arange(fft_size // 2 + 1).reshape([-1, 1]) 11 | output = multiband_linear_spectrogram(full_band_linear, 12 | keep_linear_shape=False) 13 | np.testing.assert_array_equal(output[:, 0, :].reshape([-1]), [0, 1, 2]) 14 | np.testing.assert_array_equal(output[:, 1, :].reshape([-1]), [2, 3, 4]) 15 | np.testing.assert_array_equal(output[:, 2, :].reshape([-1]), [4, 5, 6]) 16 | np.testing.assert_array_equal(output[:, 3, :].reshape([-1]), [6, 7, 8]) 17 | 18 | output = multiband_linear_spectrogram(full_band_linear, 19 | keep_linear_shape=True) 20 | np.testing.assert_array_equal(output[:, 0, :].reshape([-1]), 21 | [0, 1, 2] + [0] * 6) 22 | np.testing.assert_array_equal(output[:, 1, :].reshape([-1]), 23 | [0] * 2 + [2, 3, 4] + [0] * 4) 24 | np.testing.assert_array_equal(output[:, 2, :].reshape([-1]), 25 | [0] * 4 + [4, 5, 6] + [0] * 2) 26 | np.testing.assert_array_equal(output[:, 3, :].reshape([-1]), 27 | [0] * 6 + [6, 7, 8]) 28 | 29 | 30 | if __name__ == '__main__': 31 | unittest.main() 32 | -------------------------------------------------------------------------------- /auorange/utils.py: -------------------------------------------------------------------------------- 1 | # Copyright 2020 Yablon Ding 2 | 3 | # Licensed under the Apache License, Version 2.0 (the "License"); 4 | # you may not use this file except in compliance with the License. 5 | # You may obtain a copy of the License at 6 | 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | import matplotlib.pyplot as plt 15 | import numpy as np 16 | 17 | 18 | def plot(array): 19 | fig = plt.figure(figsize=(30, 5)) 20 | ax = fig.add_subplot(111) 21 | ax.xaxis.label.set_color('grey') 22 | ax.yaxis.label.set_color('grey') 23 | ax.xaxis.label.set_fontsize(23) 24 | ax.yaxis.label.set_fontsize(23) 25 | ax.tick_params(axis='x', colors='grey', labelsize=23) 26 | ax.tick_params(axis='y', colors='grey', labelsize=23) 27 | plt.plot(array) 28 | plt.show() 29 | 30 | 31 | def plot_spec(M): 32 | M = np.flip(M, axis=0) 33 | plt.figure(figsize=(18, 4)) 34 | plt.imshow(M, interpolation='nearest', aspect='auto') 35 | plt.show() 36 | 37 | 38 | def levinson_durbin(n, pAC): 39 | """levinson durbin's recursion 40 | 41 | Args: 42 | n (int): lpc order 43 | pAC (np.array): autocorrelation 44 | 45 | Returns: 46 | np.array: lpc coefficients 47 | """ 48 | num_frames = pAC.shape[-1] 49 | pLP = np.zeros(shape=(n, num_frames), dtype=np.float32) 50 | pTmp = np.zeros(shape=(n, num_frames), dtype=np.float32) 51 | 52 | E = np.copy(pAC[0, :]) 53 | for i in range(n): 54 | ki = np.copy(pAC[i + 1, :]) 55 | for j in range(i): 56 | ki += pLP[j, :] * pAC[i - j, :] 57 | ki = ki / E 58 | 59 | c = np.maximum(1e-5, 1 - ki * ki) 60 | E *= c 61 | 62 | pTmp[i, :] = -ki 63 | for j in range(i): 64 | pTmp[j, :] = pLP[j, :] - ki * pLP[i - j - 1, :] 65 | for j in range(i + 1): 66 | pLP[j, :] = pTmp[j, :] 67 | 68 | return pLP 69 | 70 | 71 | def multiband_linear_spectrogram(full_band_linear, keep_linear_shape=True): 72 | """split full band linear spectrogram to sub-band linear spectrogram 73 | 74 | Args: 75 | full_band_linear (np.array): full band linear spectrogram generated from mel_to_linear, 76 | shape is [FFT_SIZE // 2 + 1, num_frames] 77 | keep_linear_shape (bool, optional): whether to keep the shape of sub-band linear spectrogram 78 | same as full band linear spectrogram. Defaults to True. 79 | 80 | Returns: 81 | np.array: sub-band linear spectrograms, shape is [FFT_SIZE // 2 + 1, num_subbands, num_frames] 82 | """ 83 | num_linear_bins = full_band_linear.shape[0] 84 | fft_size = (num_linear_bins - 1) * 2 85 | num_bands = fft_size // 2 // 4 86 | get_band = lambda idx: np.expand_dims( 87 | full_band_linear[idx * num_bands:(idx + 1) * num_bands + 1, :], axis=1) 88 | if keep_linear_shape: 89 | 90 | def pad_to_linear_shape(band, idx): 91 | pad_width = [[ 92 | idx * num_bands, num_linear_bins - (idx + 1) * num_bands - 1 93 | ], [0, 0], [0, 0]] 94 | return np.pad(band, pad_width) 95 | 96 | bands = np.concatenate( 97 | [pad_to_linear_shape(get_band(i), i) for i in range(4)], axis=1) 98 | 99 | else: 100 | bands = np.concatenate([get_band(i) for i in range(4)], axis=1) 101 | return bands 102 | -------------------------------------------------------------------------------- /figs/lpc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/figs/lpc.png -------------------------------------------------------------------------------- /figs/mels.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/figs/mels.png -------------------------------------------------------------------------------- /librosa_predict.py: -------------------------------------------------------------------------------- 1 | import matplotlib.pyplot as plt 2 | 3 | from auorange import auorange 4 | from auorange.utils import plot, plot_spec 5 | 6 | wav_name = 'wavs/LJ001-0001.wav' 7 | sample_rate = 22050 8 | n_fft = 2048 9 | num_mels = 80 10 | hop_length = 275 11 | win_length = 1100 12 | lpc_order = 16 13 | clip_lpc = True 14 | 15 | wav_data = auorange.load_wav(wav_name, 22050) 16 | 17 | audio_lpc = auorange.AudioLPC(lpc_order, clip_lpc, sample_rate, f0=40.) 18 | audio_processor = auorange.LibrosaAudioFeature(sample_rate, n_fft, num_mels, 19 | hop_length, win_length, 20 | audio_lpc) 21 | 22 | mel_spec = audio_processor.mel_spectrogram(wav_data) 23 | audio, pred, error = audio_processor.lpc_audio(mel_spec, wav_data) 24 | auorange.save_wav(pred, 'wavs/pred.wav', sample_rate) 25 | auorange.save_wav(audio, 'wavs/audio.wav', sample_rate) 26 | auorange.save_wav(error, 'wavs/error.wav', sample_rate) 27 | 28 | fig = plt.figure(figsize=(30, 5)) 29 | plt.subplot(311) 30 | plt.ylabel('linear prediction') 31 | plt.xlabel('time') 32 | plt.plot(pred) 33 | plt.subplot(312) 34 | plt.ylabel('original audio') 35 | plt.xlabel('time') 36 | plt.plot(audio) 37 | plt.subplot(313) 38 | plt.ylabel('error of lpc') 39 | plt.xlabel('time') 40 | plt.plot(error) 41 | plt.show() 42 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | librosa>=0.7.0 2 | matplotlib>=3.1.1 3 | numpy>=1.17.0 4 | scipy>=1.4.1 5 | -------------------------------------------------------------------------------- /wavs/LJ001-0001.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/wavs/LJ001-0001.wav -------------------------------------------------------------------------------- /wavs/audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/wavs/audio.wav -------------------------------------------------------------------------------- /wavs/error.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/wavs/error.wav -------------------------------------------------------------------------------- /wavs/pred.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yablon/auorange/e670c5cf64f9969384bc1bef1d574e55a01d98ac/wavs/pred.wav --------------------------------------------------------------------------------