Abstract
Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model. In addition, unsupervised inference tasks such as adaptation and clustering are handled in a natural way. However, these benefits typically come at the expense of difficulties during inference. In contrast, deterministic deep neural networks are constructed in such a way that inference is straightforward, and discriminative training is relatively easy. However, their typically generic architectures often make it unclear how to incorporate specific problem knowledge or to perform flexible tasks such as unsupervised inference. This chapter introduces frameworks to provide the advantages of both approaches. To do so, we start with a model-based approach and an associated inference algorithm, and reinterpret inference iterations as layers in a deep network, while generalizing the parametrization to create a more powerful network. We show how such frameworks yield new understanding of conventional networks, and how they can result in novel networks for speech processing, including networks based on nonnegative matrix factorization, complex Gaussian microphone array signal processing, and a network inspired by efficient spectral clustering. We then discuss what has been learned in recent work and provide a prospectus for future research in this area.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Indices k in superscript always refer to the iteration index (and similarly for l defined later as the source index).
References
Attias, H.: New EM algorithms for source separation and deconvolution with a microphone array. In: Proceedings of ICASSP, vol. 5, pp. 297–300 (2003)
Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention (2014). arXiv:1412.7755
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv:1409.0473
Blei, D.M., Jordan, M.I.: Variational inference for Dirichlet process mixtures. Bayesian Anal. 1(1), 121–144 (2006)
Bregman, A.S.: Auditory Scene Analysis: The Perceptual Organization of Sound. MIT Press, Cambridge (1990)
Colson, B., Marcotte, P., Savard, G.: An overview of bilevel optimization. Ann. Oper. Res. 153(1), 235–256 (2007)
Domke, J.: Parameter learning with truncated message-passing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2937–2943 (2011)
Domke, J.: Learning graphical model parameters with approximate marginal inference. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2454 (2013)
Duong, N., Vincent, E., Gribonval, R.: Under-determined reverberant audio source separation using a full-rank spatial covariance model. IEEE Trans. Audio Speech Lang. Process. 18(7), 1830–1840 (2010)
Eggert, J., Körner, E.: Sparse coding and NMF. In: Proceedings of Neural Networks, vol. 4, pp. 2529–2533 (2004)
Erdogan, H., Hershey, J.R., Watanabe, S., Le Roux, J.: Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In: Proceedings of ICASSP (2015)
Févotte, C., Bertin, N., Durrieu, J.L.: Nonnegative matrix factorization with the Itakura–Saito divergence: with application to music analysis. Neural Comput. 21(3), 793–830 (2009)
Figueiredo, M.A.T., Jain, A.K.: Unsupervised learning of finite mixture models. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 381–396 (2002)
Goodfellow, I.J., Mirza, M., Courville, A., Bengio, Y.: Multi-prediction deep Boltzmann machines. In: Advances in Neural Information Processing Systems, pp. 548–556 (2013)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks (2013). arXiv:1302.4389
Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: ICML, pp. 399–406 (2010)
Habets, E., Benesty, J., Cohen, I., Gannot, S., Dmochowski, J.: New insights into the MVDR beamformer in room acoustics. IEEE Trans. Audio Speech Lang. Process. 18(1), 158–170 (2010)
Hershey, J.R.: Perceptual inference in generative models. Ph.D. thesis, University of California, San Diego (2005)
Hershey, J.R., Le Roux, J., Weninger, F.: Deep unfolding: model-based inspiration of novel deep architectures (2014). arXiv:1409.2574
Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S.: Deep clustering: discriminative embeddings for segmentation and separation (2015). arXiv:1508.04306
Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S.: Deep clustering: discriminative embeddings for segmentation and separation. In: Proceedings of ICASSP (2016)
Hoshen, Y., Weiss, R.J., Wilson, K.W.: Speech acoustic modeling from raw multichannel waveforms. In: Proceedings of ICASSP (2015)
Huang, P.S., Kim, M., Hasegawa-Johnson, M., Smaragdis, P.: Deep learning for monaural speech separation. In: Proceedings of ICASSP, pp. 1562–1566 (2014)
Huang, P.S., Kim, M., Hasegawa-Johnson, M., Smaragdis, P.: Joint optimization of masks and deep recurrent neural networks for monaural source separation (2015). arXiv:1502.04149
Isik, Y., Le Roux, J., Chen, Z., Watanabe, S., Hershey, J.R.: Single-channel multi-speaker separation using deep clustering. In: Proceedings of ISCA Interspeech (2016)
Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An introduction to variational methods for graphical models. Mach. Learn. 37(2), 183–233 (1999)
Kaiser, L., Sutskever, I.: Neural GPUs learn algorithms (2015). arXiv:1511.08228
Kinoshita, K., Delcroix, M., Yoshioka, T., Nakatani, T., Habets, E., Haeb-Umbach, R., Leutnant, V., Sehr, A., Kellermann, W., Maas, R.: The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech. In: Proceedings of WASPAA (2013)
Kreutz-Delgado, K.: The complex gradient operator and the CR-calculus (2009). arXiv:0906.4835
Le Roux, J., Hershey, J.R., Weninger, F.J.: Deep NMF for speech enhancement. In: Proceedings of ICASSP (2015)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: NIPS, pp. 556–562 (2001)
Li, Y., Zemel, R.: Mean field networks. In: Learning Tractable Probabilistic Models (2014)
Li, J., Deng, L., Gong, Y., Haeb-Umbach, R.: An overview of noise-robust automatic speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 22(4), 745–777 (2014)
Mairal, J., Bach, F., Ponce, J.: Task-driven dictionary learning. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 791–804 (2012)
Mandel, M.I., Weiss, R.J., Ellis, D.P.: Model-based expectation-maximization source separation and localization. IEEE Trans. Audio Speech Lang. Process. 18(2), 382–394 (2010)
Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. H. Freeman, San Francisco (1982)
Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204–2212 (2014)
Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: Proceedings of ICASSP, pp. 7092–7096 (2013)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)
Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: Proceedings of ASRU (2011)
Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: WSJCAM0: a British English speech corpus for large vocabulary continuous speech recognition. In: Proceedings of ICASSP, pp. 81–84 (1995)
Romera-Paredes, B., Torr, P.H.: Recurrent instance segmentation (2015). arXiv:1511.08250
Ross, S., Munoz, D., Hebert, M., Bagnell, J.A.: Learning message-passing inference machines for structured prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2737–2744 (2011)
Seltzer, M.L., Raj, B., Stern, R.M.: Likelihood-maximizing beamforming for robust hands-free speech recognition. IEEE Trans. Audio Speech Process. 12(5), 489–498 (2004)
Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: Proceedings of ICASSP, pp. 7398–7402 (2013)
Shental, N., Zomet, A., Hertz, T., Weiss, Y.: Pairwise clustering and graphical models. In: Advances in Neural Information Processing Systems, pp. 185–192 (2004)
Smaragdis, P., Raj, B., Shashanka, M.: Supervised and semi-supervised separation of sounds from single-channel mixtures. In: Proceedings of ICA, pp. 414–421 (2007)
Souden, M., Araki, S., Kinoshita, K., Nakatani, T., Sawada, H.: A multichannel MMSE-based framework for speech source separation and noise reduction. IEEE Trans. Audio Speech Lang. Process. 21(9), 1913–1928 (2013)
Sprechmann, P., Litman, R., Yakar, T.B., Bronstein, A.M., Sapiro, G.: Supervised sparse analysis and synthesis operators. In: NIPS, pp. 908–916 (2013)
Sprechmann, P., Bronstein, A.M., Sapiro, G.: Supervised non-Euclidean sparse NMF via bilevel optimization with applications to speech enhancement. In: Proceedings of HSCMA (2014)
Stoyanov, V., Ropson, A., Eisner, J.: Empirical risk minimization of graphical model parameters given approximate inference, decoding, and model structure. In: International Conference on Artificial Intelligence and Statistics, pp. 725–733 (2011)
Swietojanski, P., Ghoshal, A., Renals, S.: Convolutional neural networks for distant speech recognition. IEEE Signal Process. Lett. 21(9), 1120–1124 (2014)
Vincent, E., Gribonval, R., Févotte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462–1469 (2006)
Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F., Matassoni, M.: The second ‘CHiME’ speech separation and recognition challenge: datasets, tasks and baselines. In: Proceedings of ICASSP, pp. 126–130 (2013)
Wainwright, M.J., Jaakkola, T.S., Willsky, A.S.: A new class of upper bounds on the log partition function. IEEE Trans. Inf. Theory 51(7), 2313–2335 (2005)
Wang, Y., Narayanan, A., Wang, D.: On training targets for supervised speech separation. IEEE/ACM IEEE Trans. Audio Speech Lang. Process. 22(12), 1849–1858 (2014)
Weiss, Y.: Comparing the mean field method and belief propagation for approximate inference in MRFs. In: Advanced Mean Field Methods Theory and Practice, pp. 229–240 (2001)
Weninger, F., Le Roux, J., Hershey, J.R., Watanabe, S.: Discriminative NMF and its application to single-channel source separation. In: Proceedings of ISCA Interspeech (2014)
Weninger, F., Erdogan, H., Watanabe, S., Vincent, E., Le Roux, J., Hershey, J.R., Schuller, B.: Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR. In: Latent Variable Analysis and Signal Separation (LVA), pp. 91–99 (2015)
Wisdom, S., Hershey, J.R., Le Roux, J., Watanabe, S.: Deep unfolding for multichannel source separation: supplementary materials. http://www.merl.com/demos/deep-MCGMM (2015)
Wisdom, S., Hershey, J., Le Roux, J., Watanabe, S.: Deep unfolding for multichannel source separation. In: Proceedings of ICASSP, pp. 121–125 (2016)
Xu, Y., Du, J., Dai, L.R., Lee, C.H.: An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 21(1), 65–68 (2014)
Yakar, T.B., Litman, R., Sprechmann, P., Bronstein, A., Sapiro, G.: Bilevel sparse models for polyphonic music transcription. In: Proceedings of ISMIR (2013)
Yedidia, J.S., Freeman, W.T., Weiss, Y.: Constructing free-energy approximations and generalized belief propagation algorithms. IEEE Trans. Inf. Theory 51(7), 2282–2312 (2005)
Yu, D., Kolbæk, M., Tan, Z.H., Jensen, J.: Permutation invariant training of deep models for speaker-independent multi-talker speech separation (2016). arXiv:1607.00325
Zhang, X., Trmal, J., Povey, D., Khudanpur, S.: Improving deep neural network acoustic models using generalized maxout networks. In: Proceedings of ICASSP (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Hershey, J.R., Le Roux, J., Watanabe, S., Wisdom, S., Chen, Z., Isik, Y. (2017). Novel Deep Architectures in Speech Processing. In: Watanabe, S., Delcroix, M., Metze, F., Hershey, J. (eds) New Era for Robust Speech Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-64680-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-64680-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64679-4
Online ISBN: 978-3-319-64680-0
eBook Packages: Computer ScienceComputer Science (R0)