Is speech enhancement pre-processing still relevant when using deep neural networks for acoustic modeling?

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2013, Pages 2992-2996

  Delcroix, Marc ^a   Kubo, Yotaro ^a   Nakatani, Tomohiro ^a   Nakamura, Atsushi ^a  

^a Nippon Telegraph and Telephone Corporation   (Japan)

Author keywords

Deep neural network; Multi condition training; Robust speech recognition; Speech enhancement

Indexed keywords

HUMAN COMPUTER INTERACTION; SPEECH ENHANCEMENT;

AUTOMATIC SPEECH RECOGNITION; DEEP NEURAL NETWORKS; DISTANT SPEECH RECOGNITION; GAUSSIAN MIXTURE MODEL (GMMS); MULTI-CONDITION TRAININGS; ROBUST SPEECH RECOGNITION; SPEAKER VARIABILITY; TRAINING AND TESTING;

SPEECH RECOGNITION;

EID: 84906222220     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (33)

1. A. Mohamed, G. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
2. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, " IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 82-97, 2012.
3. G. Hinton, "A practical guide to training restricted Boltzmann machines, " Tech. Rep., 2010.
4. Y. Bengio, Learning deep architectures for AI. Hanover, MA, USA: Now Publishers Inc., 2009.
5. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in Proc. IEEE Workshop on Automatic Speech Recognition Understanding (ASRU), 2011, pp. 24-29.
6. A. Mohamed, G. Hinton, and G. Penn, "Understanding how deep belief networks perform acoustic modelling, " in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, pp. 4273-4276.
7. M. Woelfel and J. McDonough, Distant speech recognition. Chichester, UK: John Wiley and Sons Ltd, 2009.
8. T. Virtanen, R. Singh, and B. Raj, Technique for noise robustness in automatic speech recognition. Chichester, UK: John Wiley and Sons Ltd, 2012.
9. M. J. F. Gales and S. Young, "Robust continuous speech recognition using parallel model combination, " IEEE Transactions on Speech and Audio Processing, vol. 4, no. 5, pp. 352-359, 1996.
10. D. Y. Kim, C. K. Un, and N. S. Kim, "Speech recognition in noisy environments using first-order vector Taylor series, " Speech Communication, pp. 39-49, 1998.
11. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM adaptation using vector Taylor series for noisy speech recognition, " in Proc. International Conference on Spoken Language Processing (ICSLP), 2000, pp. 869-872.
12. R. Martin, "Noise power spectral density estimation based on optimal smoothing and minimum statistics, " IEEE Transactions on Speech and Audio Processing, vol. 9, no. 5, pp. 504-512, 2001.
13. S. Rennie, J. Hershey, and P. Olsen, "Hierarchical variational loopy belief propagation for multi-talker speech recognition, " in Proc. IEEE Workshop on Automatic Speech Recognition Understanding (ASRU), 2009, pp. 176-181.
14. T. Nakatani, S. Araki, T. Yoshioka, and M. Fujimoto, "Multichannel source separation based on source location cue with logspectral shaping by hidden Markov source model, " in Proc. Interspeech, 2010, pp. 2766-2769.
15. T. Nakatani, S. Araki, M. Delcroix, T. Yoshioka, and M. Fujimoto, "Reduction of highly nonstationary ambient noise by integrating spectral and locational characteristics of speech and noise for robust ASR, " in Proc. Interspeech, 2011, pp. 1785-1788.
16. A. Krueger and R. Haeb-Umbach, "Model-based feature enhancement for reverberant speech recognition, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, no. 7, pp. 1692-1707, 2010.
17. L. Deng, A. Acero, M. Plumpe, and X. Huang, "Large-vocabulary speech recognition under adverse acoustic environments, " in Proc. International Conference on Spoken Language Processing (ICSLP), 2000, pp. 806-809.
18. M. Delcroix, T. Nakatani, and S. Watanabe, "Combined static and dynamic variance adaptation for efficient interconnection of speech enhancement pre-processor with speech recognizer, " in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2008, pp. 4073-4076.
19. P. Simard, D. Steinkraus, and J. C. Platt, "Best practices for convolutional neural networks applied to visual document analysis, " in Proc. International Conference on Document Analysis and Recognition, 2003, pp. 958-963.
20. N. L. Roux and Y. Bengio, "Representational power of restricted Boltzmann machines and deep belief networks, " Neural Computation, vol. 20, no. 6, pp. 1631-1649, 2008.
21. T. Nakatani, T. Yoshioka, S. Araki, M. Delcroix, and M. Fujimoto, "LogMax observation model with MFCC-based spectral prior for reduction of highly nonstationary ambient noise, " in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, pp. 4029-4032.
22. T. Nakatani, T. Yoshioka, S. Araki, M. Delcroix, and M. Fujimoto, "Dominance based integration of spatial and spectral features for speech enhancement, " Submitted to IEEE Transactions on Audio, Speech, and Language Processing, 2013.
23. M. Delcroix, K. Kinoshita, T. Nakatani, S. Araki, A. Ogawa, T. Hori, S.Watanabe, M. Fujimoto, T. Yoshioka, T. Oba, Y. Kubo, M. Souden, S.-J. Hahm, and A. Nakamura, "Speech recognition in living rooms: Integrated speech enhancement and recognition system based on spatial, spectral and temporal modeling of sounds, " Computer Speech&Language, vol. 27, no. 3, pp. 851 - 873, 2013.
24. H. Sawada, S. Araki, and S. Makino, "Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 3, pp. 516-527, 2010.
25. J. Barker, E. Vincent, N. Ma, H. Christensen, and P. Green, "The PASCAL CHiME speech separation and recognition challenge, " Computer Speech&Language, vol. 27, no. 3, pp. 621 - 633, 2013.
26. J. Barker, E. Vincent, N. Ma, C. Christensen, and P. Green, "The PASCAL CHiME peech separation and recognition challenge, " http://www.dcs.shef.ac.uk/spandh/chime/challenge.html cited April 24 2012.
27. T. Hori, C. Hori, Y. Minami, and A. Nakamura, "Efficient WFSTbased one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 4, pp. 1352-1365, 2006.
28. E. McDermott, S. Watanabe, and A. Nakamura, "Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training, " in Proc. Interspeech, 2009, pp. 224-227.
29. D. Povey and P. Woodland, "Minimum phone error and Ismoothing for improved discriminative training, " in Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1. IEEE, 2002, pp. 105-108.
30. K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong, "Adaptation of context-dependent deep neural networks for automatic speech recognition, " in Proc. IEEE Spoken Language Technology Workshop (SLT), 2012, pp. 366-369.
31. Y. Tang, R. Salakhutdinov, and G. E. Hinton, "Robust Boltzmann machines for recognition and denoising, " in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, 2012, pp. 2264-2271.
32. P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol, "Extracting and composing robust features with denoising autoencoders, " in Proc. international conference on Machine learning, 2008, pp. 1096-1103.
33. A. Maas, Q. Le, T. O'Neil, O. Vinyals, P. Nguyen, and A. Ng, "Recurrent neural networks for noise reduction in robust ASR, " in Proc. Interspeech, 2012.