Environmentally robust ASR front-end for deep neural network acoustic models

Computer Speech and Language

Volumn 31, Issue 1, 2015, Pages 65-86

  Yoshioka, T ^a,b   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b NTT Communication Science Laboratories   (Japan)

Author keywords

Deep neural network; Environmental robustness; Front end; Meeting transcription

Indexed keywords

ALIGNMENT; FILTER BANKS; LOUDSPEAKERS; SPEECH ENHANCEMENT; TRANSCRIPTION;

DEEP NEURAL NETWORKS; ENVIRONMENTAL ROBUSTNESS; FEATURE TRANSFORMATIONS; FRONT-END; RELATIVE PERFORMANCE; SPEAKER ADAPTIVE TRAININGS; SPEAKER INDEPENDENTS; SPEECH RECOGNITION SYSTEMS;

SPEECH RECOGNITION;

EID: 84919935784     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2014.11.008     Document Type: Article

References (78)

1. O. Abdel-Hamid, A. Mohamed, H. Jiang, and G. Penn Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2012 4277 4280
2. K. Abed-Meraim, E. Moulines, and P. Loubaton Prediction error method for second-order blind identification IEEE Trans. Signal Process. 45 1997 694 705
3. S.F. Boll Suppression of acoustic noise in speech using spectral subtraction IEEE Trans. Acoust. Speech Signal Process. 27 1979 113 120
4. C. Breslin, K. Chen, M.J.F. Gales, and K. Knill Integrated online speaker clustering and adaptation Proc. Interspeech 2011 1085 1088
5. J. Carletta, S. Ashby, S. Bourban, M. Flynn, M. Guillemot, T. Hain, J. Kadlec, V. Karaiskos, W. Kraaij, M. Kronenthal, G. Lathoud, M. Lincoln, A. Lisowska, I. McCowan, D. Reidsma, and W.P. Wellner P The AMI meeting corpus: a pre-announcement Proceedings of International Workshop on Machine Learning for Multimodal Interaction 2006 28 39
6. S.Y. Chang, B.T. Meyer, and N. Morgan Spectro-temporal features for noise-robust speech recognition using power-law nonlinearity and power-bias subtraction Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 7063 7067
7. I. Cohen Optimal speech enhancement under signal presence uncertainty using log-spectral amplitude estimator IEEE Signal Process. Lett. 9 2002 113 116
8. I. Cohen Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging IEEE Trans. Speech Audio Process. 11 2003 466 475
9. G.E. Dahl, T.N. Sainath, and G.E. Hinton Improving deep neural networks for LVCSR using rectified linear units and dropout Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 8609 8613
10. G.E. Dahl, D. Yu, L. Deng, and A. Acero Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition IEEE Trans. Audio Speech Lang. Process. 20 2012 30 42
11. A. de la Torre, A.M. Peinado, J.C. Segura, J.L. P’erez-Córdoba, M.C. Benítez, and A.J. Rubio Histogram equalization of speech representation for robust speech recognition IEEE Trans. Audio Speech Lang. Process. 13 2005 355 366
12. L. Deng, J. Droppo, and A. Acero Enhancement of log mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise IEEE Trans. Speech Audio Process. 12 2004 133 143
13. L. Deng, J. Li, J.T. Huang, K. Yao, D. Yu, F. Seide, M. Seltzer, G. Zweig, X. He, J. Williams, Y. Gong, and A. Acero Recent advances in deep learning for speech research at Microsoft Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 8604 8608
14. L. Deng, J. Wu, J. Droppo, and A. Acero Analysis and comparison of two speech feature extraction/compensation algorithms IEEE Signal Process. Lett. 12 2005 477 480
15. J. Droppo, and A. Acero Environmental robustness J. Benesty, M.M. Sondhi, Y. Huang, Springer Handbook of Speech Processing 2008 Springer 653 679
16. J. Droppo, A. Acero, and L. Deng Evaluation of the SPLICE algorithm on the Aurora2 database Proc. Eurospeech 2001 217 220
17. J. Du, L.R. Dai, and Q. Huo Synthesized stereo mapping via deep neural networks for noisy speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2014 1764 1768
18. Y. Ephraim Speech enhancement using a minimum mean-square error log-spectral amplitude estimator IEEE Trans. Acoust. Speech Signal Process. 33 1985 443 445
19. ETSI ES 202 050 Ver. 1.1.5 Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-End Feature Extraction Algorithm; Compression Algorithms 2005
20. M.J.F. Gales Maximum likelihood linear transformations for HMM-based speech recognition Comput. Speech Lang. 12 1998 75 98
21. M.J.F. Gales Semi-tied covariance matrices for hidden Markov models IEEE Trans. Speech Audio Process. 7 1999 272 281
22. M.J.F. Gales Cluster adaptive training of hidden Markov models IEEE Trans. Speech Audio Process. 8 2000 417 428
23. M.J.F. Gales, and F. Flego Model-based approaches for degraded channel modelling in robust ASR Proc. Interspeech 2012
24. J.T. Geiger, F. Weninger, J.F. Gemmeke, M. Wöllmer, B. Schller, and G. Rigoll Memory-enhanced neural networks and NMF for robust ASR IEEE/ACM Trans. Audio Speech Lang. Process. 22 2014 1037 1046
25. O. Glembek, L. Burget, P. Matějka, M. Karafiát, and P. Kenny Simplification and optimization of i-vector extraction Proc. Int. Conf. Acoust., Speech, Signal Process. 2011 4516 4519
26. F. Grezl, M. Karafiat, S. Kontar, and J. Cernocky Probabilistic and bottle-neck features for LVCSR of meetings Proc. Int. Conf. Acoust., Speech, Signal Process. 2007 IV-757-IV-760
27. T. Hain, L. Burget, J. Dines, P.N. Garner, F. Greźl, A. El Hannani, M. Huijbregts, M. Karafiát, M. Lincoln, and V. Wan Transcribing meetings with the AMIDA systems IEEE Trans. Audio Speech Lang. Process. 20 2012 486 498
28. H. Hermansky, D. Ellis, and S. Sharma Tandem connectionist feature extraction for conventional HMM systems Proc. Int. Conf. Acoust., Speech, Signal Process. 2000 1635 1638
29. F. Hilger, and H. Ney Quantile based histogram equalization for noise robust large vocabulary speech recognition IEEE Trans. Audio Speech Lang. Process. 14 2006 845 854
30. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kinsgbury Deep neural networks for acoustic modeling in speech recognition IEEE Signal Process. Mag. 29 2012 82 97
31. O. Kalini, M.L. Seltzer, J. Droppo, and A. Acero Noise adaptive training for robust automatic speech recognition IEEE Trans. Audio Speech Lang. Process. 18 2010 1889 1901
32. H. Kameoka, T. Nakatani, and T. Yoshioka Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms Proc. Int. Conf. Acoust., Speech, Signal Process. 2009 45 48
33. C. Kim, and R.M. Sterm Power-normalized cepstral coefficients (pncc) for robust speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2012 4101 4104
34. K.M. Knill, M.J.F. Gales, S.P. Rath, P.C. Woodland, C. Zhang, and S.X. Zhang Investigation of multilingual deep neural networks for spoken term detection Proc. Workshop on Automatic Speech Recognition and Understanding 2013 138 143
35. A. Krueger, and R. Haeb-Umbach Model-based feature enhancement for reverberant speech recognition IEEE Trans. Audio Speech Lang. Process. 18 2010 1692 1707
36. K. Lebart, J.M. Boucher, and P.N. Denbigh A new method based on spectral subtraction for speech dereverberation Acta Acust. Unit. Acust. 87 2001 359 366
37. B. Li, and K.C. Sim Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems Proc. Interspeech 2010 526 529
38. B. Li, and K.C. Sim Noise adaptive front-end normalization based on vector Taylor series for deep neural networks in robust speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 7408 7412
39. B. Li, and K.C. Sim An ideal hidden-activation mask for deep neural networks based noise-robust speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2014 200 204
40. H. Liao Speaker adaptation of context dependent deep neural networks Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 7947 7951
41. L. Lu, K.K. Chin, A. Ghoshal, and S. Renals Joint uncertainty decoding for noise robust subspace Gaussian mixture models IEEE Trans. Audio Speech Lang. Process. 21 2013 1791 1804
42. D. Macho, L. Mauuary, B. Noé, Y.M. Cheng, D. Ealey, D. Jouvet, H. Kelleher, D. Pearce, and F. Saadoun Evaluation of a noise-robust DSR front-end on AURORA databases Proc. Int. Conf. Spoken Language Process. 2002 17 20
43. A. Mohamed, G.E. Dahl, and G. Hinton Acoustic modeling using deep belief networks IEEE Trans. Audio Speech Lang. Process. 20 2012 14 22
44. A. Mohamed, G. Hinton, and G. Penn Understanding how deep belief networks perform acoustic modelling Proc. Int. Conf. Acoust., Speech, Signal Process. 2012 4273 4276
45. P.J. Moreno, B. Raj, and R.M. Stern A vector Taylor series approach for environmental-independent speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 1996 733 736
46. N. Morgan, and H. Bourlard Continuous speech recognition: an introduction to the hybrid HMM/connectionist approach IEEE Signal Process. Mag. 12 1995 24 42
47. A. Narayanan, and D. Wang Joint noise adaptive training for robust automatic speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2014 2523 2527
48. J.P. Neto, C. Martins, and L.B. Almeida Speaker-adaptation in a hybrid HMM-MLP recognizer Proc. Int. Conf. Acoust., Speech, Signal Process. 1996 3382 3385
49. J. Park, F. Diehl, M.J.F. Gales, M. Tomalin, and P.C. Woodland The efficient incorporation of MLP features into automatic speech recognition systems Comput. Speech Lang. 25 2011 519 534
50. S.D. Peters, P. Stubley, and J.M. Valin On the limits of speech recognition in noise Proc. Int. Conf. Acoust., Speech, Signal Process. 1999 365 368
51. C. Plahl, R. Schlüter, and H. Ney Improved acoustic feature combination for LVCSR by neural networks Proc. Interspeech 2011 1237 1240
52. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig FMPE: Discriminatively trained features for speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2005 961 964
53. S. Renals, N. Morgan, H. Bourlard, M. Cohen, and H. Franco Connectionist probability estimators in HMM speech recognition IEEE Trans. Speech Audio Process. 2 1994 161 174
54. S. Renals, and P. Swietojanski Neural networks for distant speech recognition Proc. Joint Workshop Hands-free Speech Commun. Microphone Arrays 2014 172 176
55. S. Rennie, P. Dognin, and P. Fousek Robust speech recognition using dynamic noise adaptation Proc. Int. Conf. Acoust., Speech, Signal Process. 2011 4592 4595
56. T.N. Sainath, B.r. Kingsbury, A. Mohamed, and B. Ramabhadran Learning filter banks within a deep neural network framework Proc. Workshop on Automatic Speech Recognition and Understanding 2013 297 302
57. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny Speaker adaptation of neural network acoustic models using i-vectors Proc. Workshop on Automatic Speech Recognition and Understanding 2013 55 59
58. R. Schlüter, I. Bezrukov, H. Wagner, and H. Ney Gammatone features and feature combination for large vocabulary speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2007 IV-649-IV-652
59. F. Seide, G. Li, X. Chen, and D. Yu Feature engineering in context-dependent deep neural networks for conversational speech transcription Proc. Workshop on Automatic Speech Recognition and Understanding 2011 24 29
60. M.L. Seltzer, D. Yu, and Y. Wang An investigation of deep neural networks for noise robust speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 7398 7402
61. Y. Shinohara, and M. Akamine Bayesian feature enhancement using a mixture of unscented transformations for uncertainty decoding of noisy speech Proc. Int. Conf. Acoust., Speech, Signal Process. 2009 4569 4572
62. A. Stolcke Making the most from multiple microphones in meeting recordings Proc. Int. Conf. Acoust., Speech, Signal Process. 2011 4992 4995
63. V. Stouten Robust automatic speech recognition in time-varying environments 2006 Katholieke University Leuven Ph.D. Thesis
64. P. Swietojanski, A. Ghoshal, and S. Renals Hybrid acoustic models for distant multichannel large vocabulary speech recognition Proc. Workshop on Automatic Speech Recognition and Understanding 2013 285 290
65. I. Tashev Sound Capture and Processing: Practical Approaches 2009 Wiley
66. S.S. Thomas, S. Ganapathy, and H. Hermansky Recognition of reverberant speech using frequency domain linear prediction IEEE Signal Process. Lett. 2008 681 684
67. Y. Wang, and M.J.F. Gales Speaker and noise factorization for robust speech recognition IEEE Trans. Audio Speech Lang. Process. 20 2012 2149 2158
68. F. Weninger, S. Watanabe, Y. Tachioka, and B. Schuller Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2014 4656 4660
69. K. Yao, Y. Gong, and C. Liu A feature space transformation method for personalization using generalized i-vector clustering Proc. Interspeech 2011
70. K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong Adaptation of context-dependent deep neural networks for automatic speech recognition Proc. IEEE Workshop on Spoken Language Technology 2012 366 369
71. T. Yoshioka, X. Chen, and M.J.F. Gales Impact of single-microphone dereverberation on DNN-based meeting transcription systems Proc. Int. Conf. Acoust., Speech, Signal Process. 2014 5527 5531
72. T. Yoshioka, and T. Nakatani Generalization of multi-channel linear prediction methods for blind MIMO impulse response shortening IEEE Trans. Audio Speech Lang. Process. 20 2012 2707 2720
73. T. Yoshioka, and T. Nakatani Noise model transfer: novel approach to robustness against nonstationary noise IEEE Trans. Audio Speech Lang. Process. 21 2013 2182 2192
74. T. Yoshioka, A. Sehr, M. Delcroix, K. Kinoshita, R. Maas, T. Nakatani, and W. Kellermann Making machines understand us in reverberant rooms: robustness against reverberation for automatic speech recognition IEEE Signal Process. Mag. 29 2012 114 126
75. T. Yoshioka, H. Tachibana, T. Nakatani, and M. Miyoshi Adaptive dereverberation of speech signals with speaker-position change detection Proc. Int. Conf. Acoust., Speech, Signal Process. 2009 3733 3736
76. S.J. Young, G. Evermann, M.J.F. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P.C. Woodland The HTK Book version 3.4.1 2009 Cambridge University Engineering Department Cambridge, UK
77. D. Yu, L. Deng, J. Droppo, J. Wu, Y. Gong, and A. Acero Robust speech recognition using a cepstral minimum-mean-square-error-motivated noise suppressor IEEE Trans. Audio Speech Lang. Process. 16 2008 1061 1070
78. D. Yu, K. Yao, H. Su, G. Li, and F. Seide KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition Proc. Int. Conf. Acoust., Speech, Signal Process. 2013 7893 7897