摘要:本文提出了一种面向深度学习语音增强模型的压缩方法。该方法不依赖于开源代码,鼓励研究者参考现有成果进行创新。作者为中国研究者,在语音增强领域拥有多年经验,引用格式为:Tan K, Wang D L. Towards model compression[J]. 2023, 12(3): 45-58.
论文地址:面向基于深度学习的语音增强模型压缩
论文代码:没开源,鼓励大家去向作者要呀,作者是中国人,在语音增强领域 深耕多年
引用格式:Tan K, Wang D L. Towards model compression for deep learning based speech enhancement[J]. IEEE/ACM transactions on audio, speech, and language processing, 2021, 29: 1785-1794.
[1] L. J. Ba and R. Caruana, Do deep nets really need to be deep? , in Proc. 27th Int. Conf. Neural Inf. Process. Syst. , vol. 2, 2014, pp. 2654 2662,.
[2] Y. Chebotar and A. Waters, Distilling knowledge from ensembles of neural networks for speech recognition, in Proc. Annu. Conf. Int.Speech Commun. Assoc. (INTERSPEECH), 2016, pp. 3439 3443.
[3] Y. Chen, T. Guan, and C.Wang, Approximate nearest neighbor search by residual vector quantization, Sensors, vol. 10, no. 12, pp. 11259 11273, 2010.
[4] L. Deng, G. Li, S. Han, L. Shi, and Y. Xie, Model compression and hardware acceleration for neural networks: A comprehensive survey, Proc. IEEE IRE, vol. 108, no. 4, pp. 485 532, Apr. 2020.
[5] E.Denton,W. Zaremba, J. Bruna,Y. LeCun, andR. Fergus, Exploiting linear structure within convolutional networks for efficient evaluation, Proc. 27th Int.Conf. Neural Inf. Process. Syst. , vol. 1, 2014, pp. 1269 1277,.
[6] I. Fedorov et al., TinyLSTMs: Efficient neural speech enhancement for hearing aids, in INTERSPEECH, 2020, pp. 4054 4058.
[7] J. Friedman, T. Hastie, and R. Tibshirani, A. note on the group lasso and a sparse group lasso, 2010, arXiv:1001.0736.
[8] J. Garofolo, D. Graff, D. Paul, and D. Pallett, CSR-I (WSJ0) Complete LDC93S6A, Web Download. Philadelphia: Linguistic Data Consortium, vol. 83, 1993.
[9] X. Glorot, A. Bordes, and Y. Bengio, Deep sparse rectifier neural networks, in Proc. 14th Int. Conf. Artif. Intell.Statist.. JMLR Workshop, 2011, pp. 315 323.
[10] Y. Gong, L. Liu, M. Yang, and L. Bourdev, Compressing deep convolutional networks using vector quantization, 2014, arXiv:1412.6115.
[11] S. Han, H. Mao, and W. J. Dally, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, in Proc. Int. Conf. Learn. Representations, 2015.
[12] B. Hassibi andD.G. Stork, Second order derivatives for network pruning: Optimal brain surgeon, in Proc. Adv. Neural Inf. Process. Syst., 1993, pp. 164 171.
[13] Y. He, X. Zhang, and J. Sun, Channel pruning for accelerating very deep neural networks, in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 1389 1397.
[14] J. R. Hershey, Z. Chen, J. Le Roux, and S. Watanabe, Deep clustering: Discriminative embeddings for segmentation and separation, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2016, pp. 31 35.
[15] G. Hinton, O. Vinyals, and J. Dean, Distilling the knowledge in a neural network, in Proc. Int. Conf. Neural Inf. Process. Syst. Deep Learn. Representation Learn. Workshop, 2015.
[16] A. G. Howard et al., MobileNets: Efficient convolutional neural networks for mobile vision applications. 2017, arXiv:1704.04861.
[17] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and <5 MB model size . 2016, arXiv:1602.07360.
[18] B. Jacob et al., Quantization and training of neural networks for efficient integer-arithmetic-only inference, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 2704 2713.
[19] H. Jegou, M. Douze, and C. Schmid, Product quantization for nearest neighbor search, IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 1, pp. 117 128, Jan. 2010.
[20] J. Jensen and C. H. Taal, An algorithm for predicting the intelligibility of speech masked by modulated noise maskers, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 24, no. 11, pp. 2009 2022, Nov. 2016.
[21] M.Kolbæk,D.Yu, Z.-H. Tan, and J. Jensen, Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 25, no. 10, pp. 1901 1913, Oct. 2017.
[22] R. Krishnamoorthi, Quantizing deep convolutional networks for efficient inference: A whitepaper, 2018, arXiv:1806.08342.
[23] Y. LeCun, J. S. Denker, and S. A. Solla, Optimal brain damage, in Proc. Adv. Neural Inf. Process. Syst., 1990, pp. 598 605.
[24] J. Lin, Y. Rao, J. Lu, and J. Zhou, Runtime neural pruning, in Proc. 31st Int. Conf. Neural Inf. Process. Syst., 2017, pp. 2178 2188.
[25] Y.-C. Lin, Y.-T. Hsu, S.-W. Fu, Y. Tsao, and T.-W. Kuo, IA-NET: Acceleration and compression of speech enhancement using integer-adder deep neural network, in INTERSPEECH, 2019, pp. 1801 1805.
[26] Y. Liu and D. L. Wang, Divide and conquer: A deep CASA approach to talker-independent monaural speaker separation, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 27, no. 12, pp. 2092 2102, Dec. 2019.
[27] L. Lu,M. Guo, and S. Renals, Knowledge distillation for small-footprint highway networks, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2017, pp. 4820 4824.
[28] J.-H. Luo, J. Wu, and W. Lin, ThiNet: A filter level pruning method for deep neural network compression, in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 5058 5066.
[29] Y. Luo and N. Mesgarani, Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation, IEEE/ACM Trans Audio, Speech, Lang. Process., vol. 27, no. 8, pp. 1256 1266, Aug. 2019.
[30] H. Mao et al., Exploring the granularity of sparsity in convolutional neural networks, in Proc. IEEE Conf.Comput. Vis. Pattern Recognit.Workshops, 2017, pp. 13 20.
[31] P. Molchanov, A. Mallya, S. Tyree, I. Frosio, and J. Kautz, Importance estimation for neural network pruning, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2019, pp. 11264 11272.
[32] A. Pandey and D. L. Wang, TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2019, pp. 6875 6879.
[33] S. J. Reddi, S. Kale, and S. Kumar, On the convergence of adam and beyond, in Proc. Int. Conf. Learn. Representations, 2018.
[34] R. Reed, Pruning algorithms-a survey, IEEE Trans. Neural Netw. , vol. 4, no. 5, pp. 740 747, Sep. 1993.
[35] A. W. Rix, J. G. Beerends, M. P. Hollier, and A. P. Hekstra, Perceptual evaluation of speech quality (PESQ)-A new method for speech quality assessment of telephone networks and codecs, in Proc. IEEE Int. Conf. Acoust. , Speech, Signal Process. (Cat. No 01CH37221), vol. 2, 2001, pp. 749 752.
[36] A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, FitNets: Hints for thin deep nets, in Int. Conf. Learn. Representations, 2015.
[37] S. Scardapane, D. Comminiello, A. Hussain, and A. Uncini, Group sparse regularization for deep neural networks, Neurocomputing, vol. 241, pp. 81 89, 2017.
[38] N. Simon, J. Friedman, T. Hastie, and R. Tibshirani, A. sparse-group lasso, J. Comput. Graphical Statist. , vol. 22, no. 2, pp. 231 245, 2013.
[39] C. H. Taal, R. C. Hendriks, R. Heusdens, and J. Jensen, An algorithm for intelligibility prediction of time-frequency weighted noisy speech, IEEE Trans. Audio, Speech, Lang. Process. , vol. 19, no. 7, pp. 2125 2136, Sep. 2011.
[40] K. Tan and D. L. Wang, Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement, IEEE/ACM Trans. Audio, Speech, Lang. Process. , vol. 28, pp. 380 390, 2020.
[41] K. Tan and D. L. Wang, Compressing deep neural networks for efficient speech enhancement, in Proc. IEEE Int. Conf. Acoust. , Speech Signal Process. 2021, pp. 8358 8362.
[42] J. Thiemann, N. Ito, and E. Vincent, The diverse environments multichannel acoustic noise database: A database of multichannel environmental noise recordings, J. Acoust. Soc. Amer. , vol. 133, no. 5, pp. 3591 3591, 2013.
[43] A. Varga and H. J. Steeneken, Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems, Speech Commun. , vol. 12, no. 3, pp. 247 251, 1993.
[44] E. Vincent, R. Gribonval, and C. Févotte, Performance measurement in blind audio source separation, IEEE Trans. Audio, Speech, Lang. Process. , vol. 14, no. 4, pp. 1462 1469, Jul. 2006.
[45] D. L. Wang, On ideal binary mask as the computational goal of auditory scene analysis, in P. Divenyi, ed., Speech Separation by Humans Machines. Springer, 2005, pp. 181 197.
[46] D. L. Wang and G. J. Brown, editors. Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Hoboken, NJ, USA, Wiley, 2006.
[47] D. L. Wang and J. Chen, Supervised speech separation based on deep learning: An overview, IEEE/ACMTrans. Audio, Speech, Lang. Process. , vol. 26, no. 10, pp. 1702 1726, Oct. 2018.
[48] Y. Wang, A. Narayanan, and D. L. Wang, On training targets for supervised speech separation, IEEE/ACM Trans. Audio, Speech, Lang. Process. , vol. 22, no. 12, pp. 1849 1858, Dec. 2014.
[49] J.-Y. Wu, C. Yu, S.-W. Fu, C.-T. Liu, S.-Y. Chien, and Y. Tsao, Increasing compactness of deep learning based speech enhancement models with parameter pruning and quantization techniques, IEEE Signal Process. Lett. , vol. 26, no. 12, pp. 1887 1891, Dec. 2019.
[50] F. Ye, Y. Tsao, and F. Chen, Subjective feedback-based neural network pruning for speech enhancement, in Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf., 2019, pp. 673 677.
[51] R. Yu et al., NISP: Pruning networks using neuron importance score propagation, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 9194 9203.
[52] X. Zhang, X. Zhou, M. Lin, and J. Sun, ShuffleNet: An extremely efficient convolutional neural network for mobile devices, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 6848 6856.
摘要:本文提出了一种面向深度学习语音增强模型的压缩方法。该方法不依赖于开源代码,鼓励研究者参考现有成果进行创新。作者为中国研究者,在语音增强领域拥有多年经验,引用格式为:Tan K, Wang D L. Towards model compression[J]. 2023, 12(3): 45-58.
论文地址:面向基于深度学习的语音增强模型压缩
论文代码:没开源,鼓励大家去向作者要呀,作者是中国人,在语音增强领域 深耕多年
引用格式:Tan K, Wang D L. Towards model compression for deep learning based speech enhancement[J]. IEEE/ACM transactions on audio, speech, and language processing, 2021, 29: 1785-1794.
[1] L. J. Ba and R. Caruana, Do deep nets really need to be deep? , in Proc. 27th Int. Conf. Neural Inf. Process. Syst. , vol. 2, 2014, pp. 2654 2662,.
[2] Y. Chebotar and A. Waters, Distilling knowledge from ensembles of neural networks for speech recognition, in Proc. Annu. Conf. Int.Speech Commun. Assoc. (INTERSPEECH), 2016, pp. 3439 3443.
[3] Y. Chen, T. Guan, and C.Wang, Approximate nearest neighbor search by residual vector quantization, Sensors, vol. 10, no. 12, pp. 11259 11273, 2010.
[4] L. Deng, G. Li, S. Han, L. Shi, and Y. Xie, Model compression and hardware acceleration for neural networks: A comprehensive survey, Proc. IEEE IRE, vol. 108, no. 4, pp. 485 532, Apr. 2020.
[5] E.Denton,W. Zaremba, J. Bruna,Y. LeCun, andR. Fergus, Exploiting linear structure within convolutional networks for efficient evaluation, Proc. 27th Int.Conf. Neural Inf. Process. Syst. , vol. 1, 2014, pp. 1269 1277,.
[6] I. Fedorov et al., TinyLSTMs: Efficient neural speech enhancement for hearing aids, in INTERSPEECH, 2020, pp. 4054 4058.
[7] J. Friedman, T. Hastie, and R. Tibshirani, A. note on the group lasso and a sparse group lasso, 2010, arXiv:1001.0736.
[8] J. Garofolo, D. Graff, D. Paul, and D. Pallett, CSR-I (WSJ0) Complete LDC93S6A, Web Download. Philadelphia: Linguistic Data Consortium, vol. 83, 1993.
[9] X. Glorot, A. Bordes, and Y. Bengio, Deep sparse rectifier neural networks, in Proc. 14th Int. Conf. Artif. Intell.Statist.. JMLR Workshop, 2011, pp. 315 323.
[10] Y. Gong, L. Liu, M. Yang, and L. Bourdev, Compressing deep convolutional networks using vector quantization, 2014, arXiv:1412.6115.
[11] S. Han, H. Mao, and W. J. Dally, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, in Proc. Int. Conf. Learn. Representations, 2015.
[12] B. Hassibi andD.G. Stork, Second order derivatives for network pruning: Optimal brain surgeon, in Proc. Adv. Neural Inf. Process. Syst., 1993, pp. 164 171.
[13] Y. He, X. Zhang, and J. Sun, Channel pruning for accelerating very deep neural networks, in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 1389 1397.
[14] J. R. Hershey, Z. Chen, J. Le Roux, and S. Watanabe, Deep clustering: Discriminative embeddings for segmentation and separation, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2016, pp. 31 35.
[15] G. Hinton, O. Vinyals, and J. Dean, Distilling the knowledge in a neural network, in Proc. Int. Conf. Neural Inf. Process. Syst. Deep Learn. Representation Learn. Workshop, 2015.
[16] A. G. Howard et al., MobileNets: Efficient convolutional neural networks for mobile vision applications. 2017, arXiv:1704.04861.
[17] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and <5 MB model size . 2016, arXiv:1602.07360.
[18] B. Jacob et al., Quantization and training of neural networks for efficient integer-arithmetic-only inference, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 2704 2713.
[19] H. Jegou, M. Douze, and C. Schmid, Product quantization for nearest neighbor search, IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 1, pp. 117 128, Jan. 2010.
[20] J. Jensen and C. H. Taal, An algorithm for predicting the intelligibility of speech masked by modulated noise maskers, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 24, no. 11, pp. 2009 2022, Nov. 2016.
[21] M.Kolbæk,D.Yu, Z.-H. Tan, and J. Jensen, Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 25, no. 10, pp. 1901 1913, Oct. 2017.
[22] R. Krishnamoorthi, Quantizing deep convolutional networks for efficient inference: A whitepaper, 2018, arXiv:1806.08342.
[23] Y. LeCun, J. S. Denker, and S. A. Solla, Optimal brain damage, in Proc. Adv. Neural Inf. Process. Syst., 1990, pp. 598 605.
[24] J. Lin, Y. Rao, J. Lu, and J. Zhou, Runtime neural pruning, in Proc. 31st Int. Conf. Neural Inf. Process. Syst., 2017, pp. 2178 2188.
[25] Y.-C. Lin, Y.-T. Hsu, S.-W. Fu, Y. Tsao, and T.-W. Kuo, IA-NET: Acceleration and compression of speech enhancement using integer-adder deep neural network, in INTERSPEECH, 2019, pp. 1801 1805.
[26] Y. Liu and D. L. Wang, Divide and conquer: A deep CASA approach to talker-independent monaural speaker separation, IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 27, no. 12, pp. 2092 2102, Dec. 2019.
[27] L. Lu,M. Guo, and S. Renals, Knowledge distillation for small-footprint highway networks, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2017, pp. 4820 4824.
[28] J.-H. Luo, J. Wu, and W. Lin, ThiNet: A filter level pruning method for deep neural network compression, in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 5058 5066.
[29] Y. Luo and N. Mesgarani, Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation, IEEE/ACM Trans Audio, Speech, Lang. Process., vol. 27, no. 8, pp. 1256 1266, Aug. 2019.
[30] H. Mao et al., Exploring the granularity of sparsity in convolutional neural networks, in Proc. IEEE Conf.Comput. Vis. Pattern Recognit.Workshops, 2017, pp. 13 20.
[31] P. Molchanov, A. Mallya, S. Tyree, I. Frosio, and J. Kautz, Importance estimation for neural network pruning, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2019, pp. 11264 11272.
[32] A. Pandey and D. L. Wang, TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain, in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2019, pp. 6875 6879.
[33] S. J. Reddi, S. Kale, and S. Kumar, On the convergence of adam and beyond, in Proc. Int. Conf. Learn. Representations, 2018.
[34] R. Reed, Pruning algorithms-a survey, IEEE Trans. Neural Netw. , vol. 4, no. 5, pp. 740 747, Sep. 1993.
[35] A. W. Rix, J. G. Beerends, M. P. Hollier, and A. P. Hekstra, Perceptual evaluation of speech quality (PESQ)-A new method for speech quality assessment of telephone networks and codecs, in Proc. IEEE Int. Conf. Acoust. , Speech, Signal Process. (Cat. No 01CH37221), vol. 2, 2001, pp. 749 752.
[36] A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, FitNets: Hints for thin deep nets, in Int. Conf. Learn. Representations, 2015.
[37] S. Scardapane, D. Comminiello, A. Hussain, and A. Uncini, Group sparse regularization for deep neural networks, Neurocomputing, vol. 241, pp. 81 89, 2017.
[38] N. Simon, J. Friedman, T. Hastie, and R. Tibshirani, A. sparse-group lasso, J. Comput. Graphical Statist. , vol. 22, no. 2, pp. 231 245, 2013.
[39] C. H. Taal, R. C. Hendriks, R. Heusdens, and J. Jensen, An algorithm for intelligibility prediction of time-frequency weighted noisy speech, IEEE Trans. Audio, Speech, Lang. Process. , vol. 19, no. 7, pp. 2125 2136, Sep. 2011.
[40] K. Tan and D. L. Wang, Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement, IEEE/ACM Trans. Audio, Speech, Lang. Process. , vol. 28, pp. 380 390, 2020.
[41] K. Tan and D. L. Wang, Compressing deep neural networks for efficient speech enhancement, in Proc. IEEE Int. Conf. Acoust. , Speech Signal Process. 2021, pp. 8358 8362.
[42] J. Thiemann, N. Ito, and E. Vincent, The diverse environments multichannel acoustic noise database: A database of multichannel environmental noise recordings, J. Acoust. Soc. Amer. , vol. 133, no. 5, pp. 3591 3591, 2013.
[43] A. Varga and H. J. Steeneken, Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems, Speech Commun. , vol. 12, no. 3, pp. 247 251, 1993.
[44] E. Vincent, R. Gribonval, and C. Févotte, Performance measurement in blind audio source separation, IEEE Trans. Audio, Speech, Lang. Process. , vol. 14, no. 4, pp. 1462 1469, Jul. 2006.
[45] D. L. Wang, On ideal binary mask as the computational goal of auditory scene analysis, in P. Divenyi, ed., Speech Separation by Humans Machines. Springer, 2005, pp. 181 197.
[46] D. L. Wang and G. J. Brown, editors. Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Hoboken, NJ, USA, Wiley, 2006.
[47] D. L. Wang and J. Chen, Supervised speech separation based on deep learning: An overview, IEEE/ACMTrans. Audio, Speech, Lang. Process. , vol. 26, no. 10, pp. 1702 1726, Oct. 2018.
[48] Y. Wang, A. Narayanan, and D. L. Wang, On training targets for supervised speech separation, IEEE/ACM Trans. Audio, Speech, Lang. Process. , vol. 22, no. 12, pp. 1849 1858, Dec. 2014.
[49] J.-Y. Wu, C. Yu, S.-W. Fu, C.-T. Liu, S.-Y. Chien, and Y. Tsao, Increasing compactness of deep learning based speech enhancement models with parameter pruning and quantization techniques, IEEE Signal Process. Lett. , vol. 26, no. 12, pp. 1887 1891, Dec. 2019.
[50] F. Ye, Y. Tsao, and F. Chen, Subjective feedback-based neural network pruning for speech enhancement, in Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf., 2019, pp. 673 677.
[51] R. Yu et al., NISP: Pruning networks using neuron importance score propagation, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 9194 9203.
[52] X. Zhang, X. Zhou, M. Lin, and J. Sun, ShuffleNet: An extremely efficient convolutional neural network for mobile devices, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 6848 6856.