Uncertainty-based learning of acoustic models from noisy data

Computer Speech and Language

Volumn 27, Issue 3, 2013, Pages 874-894

  Ozerov, Alexey ^a   Lagrange, Mathieu ^b   Vincent, Emmanuel ^c  

^a Technicolor Research and Innovation ^*  (France)

^b CNRS   (France)

^c INRIA   (France)

Author keywords

Acoustic model; Classification; Expectation maximization; Gaussian mixture model; Hidden Markov model; Noisy data; Training; Uncertainty

Indexed keywords

AUDIO ACOUSTICS; CLASSIFICATION (OF INFORMATION); COMMUNICATION CHANNELS (INFORMATION THEORY); DECODING; GAUSSIAN DISTRIBUTION; HIDDEN MARKOV MODELS; IMAGE SEGMENTATION; MARKOV PROCESSES; MAXIMUM LIKELIHOOD; MAXIMUM LIKELIHOOD ESTIMATION; MAXIMUM PRINCIPLE; OBJECT RECOGNITION; PERSONNEL TRAINING; TRELLIS CODES; UNCERTAINTY ANALYSIS;

ACOUSTIC MODEL; EXPECTATION - MAXIMIZATIONS; GAUSSIAN MIXTURE MODEL; NOISY DATA; UNCERTAINTY;

SPEECH RECOGNITION;

EID: 84905275072     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2012.07.002     Document Type: Article

References (40)

1. K. Adiloʇlu, and E. Vincent An uncertainty estimation approach for the extraction of individual source features in multisource recordings EUSIPCO, 19th European Signal Processing Conference 2011 1663 1667
2. S. Arberet, A. Ozerov, F. Bimbot, and R. Gribonval A tractable framework for estimating and combining spectral source models for audio source separation Signal Processing 92 8 2012 1886 1901
3. Astudillo, R.F., 2010. Integration of short-time Fourier domain speech enhancement and observation uncertainty techniques for robust automatic speech recognition. Ph.D. thesis, Technical University Berlin.
4. J. Barker, E. Vincent, N. Ma, H. Christensen, and P. Green "The PASCAL CHiME Speech Separation and Recognition Challenge" Computer Speech and Language 27 3 2013 621 633
5. J.P. Barker, M.P. Cooke, and D.P.W. Ellis Decoding speech in the presence of other sources Speech Communication 45 1 2005 5 25
6. C.M. Bishop Pattern Recognition and Machine Learning 2006 Springer
7. M. Cooke Robust automatic speech recognition with missing and unreliable acoustic data Speech Communication 34 3 2001, June 267 285
8. 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 the presence of highly non-stationary noise based on spatial, spectral and temporal speech/noise modeling combined with dynamic variance adaptation Proc. 1st Int. Workshop on Machine Listening in Multisource Environments (CHiME) 2011 12 17
9. M. Delcroix, T. Nakatani, and S. Watanabe Static and dynamic variance compensation for recognition of reverberant speech with dereverberation preprocessing IEEE Transactions on Audio, Speech and Language Processing 17 2 2009 324 334
10. A.P. Dempster, N.M. Laird, and D.B. Rubin Maximum likelihood from incomplete data via the EM algorithm Journal of the Royal Statistical Society. Series B (Methodological) 39 1977 1 38
11. L. Deng, A. Acero, M. Plumpe, and X. Huang Large vocabulary speech recognition under adverse acoustic environments Proc. 6th Int. Conf. on Spoken Language Processing (ICSLP) 2000 806 809
12. L. Deng, J. Droppo, and A. Acero Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion IEEE Transactions on Speech and Audio Processing 13 3 2005 412 421
13. J. Droppo, and A. Acero Environmental robustness J. Benesty, M.M. Sondhi, Y. Huang, Handbook of Speech Processing 2008 Springer pp. 653-680
14. Y. Ephraim Statistical-model-based speech enhancement systems Proceedings of the IEEE 80 10 1992 1526 1555
15. S. Fischer, and K.-D. Kammeyer Broadband beamforming with adaptive postfiltering for speech acquisition in noisy environments IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'97) 1997 359 362 Vol. 1
16. Gales, M.J.F., September 1995. Model-based techniques for noise robust speech recognition. Ph.D. thesis, University of Cambridge, UK.
17. M.J.F. Gales Model-based approaches to handling uncertainty D. Kolossa, R. Haeb-Umbach, Robust Speech Recognition of Uncertain or Missing Data - Theory and Applications 2011 Springer Berlin, Germany pp. 101-125
18. J.-L. Gauvain, and C.-H. Lee Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains IEEE Transactions on Speech and Audio Processing 2 2 1994 291 298
19. Z. Ghahramani, and M. Jordan Supervised learning from incomplete data via an EM approach Advance on Neural Information Processing Systems 1994 120 127
20. C.M. Grinstead, and J.L. Snell Introduction to Probability 2nd ed. 1997 American Mathematical Society Providence, RI
21. D. Kolossa, R.F. Astudillo, A. Abad, S. Zeiler, R. Saeidi, P. Mowlaee, J. da Silva Neto, and R. Martin CHIME challenge: approaches to robustness using beamforming and uncertainty-of-observation techniques Proc. 1st Int. Workshop on Machine Listening in Multisource Environments (CHiME) 2011 6 11
22. D. Kolossa, R.F. Astudillo, E. Hoffmann, and R. Orglmeister Independent component analysis and time-frequency masking for speech recognition in multitalker conditions EURASIP Journal on Audio, Speech, and Music Processing 2010 2010 1 14
23. C. Leggetter, and P. Woodland Flexible speaker adaptation using maximum likelihood linear regression ARPA Spoken Lang. Technol. Workshop 1995 104 109
24. H. Liao, and M.J.F. Gales Adaptive training with joint uncertainty decoding for robust recognition of noisy data Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'07) 2007 389 392 Vol. 4
25. P.J. Moreno, B. Raj, and R.M. Stern A vector Taylor series approach for environment-independent speech recognition IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'96) 1996 733 736 Vol. 2
26. J.G. Moreno-Torres, T. Raeder, R. Alaiz-Rodríguez, N.V. Chawla, and F. Herrera A unifying view on dataset shift in classification Pattern Recognition 45 1 January 2012 521 530
27. C. Nadeu, P. Pachès-Leal, and B.-H. Juang Filtering time sequences of spectral parameters for speech recognition Speech Communication 22 1997 315 332
28. A. Ozerov, M. Lagrange, and E. Vincent GMM-based classification from noisy features Proc. 1st Int. Workshop on Machine Listening in Multisource Environments (CHiME) Florence, Italy September 2011 pp. 30-35
29. Ozerov, A., Lagrange, M., Vincent, E., 2012. Acoustic Model Uncertainty Learning Experimental Toolbox (AMULET), http://bass-db.gforge.inria.fr/amulet/.
30. A. Ozerov, P. Philippe, F. Bimbot, and R. Gribonval Adaptation of Bayesian models for single-channel source separation and its application to voice/music separation in popular songs IEEE Transactions on Audio, Speech and Language Processing 15 5 2007 1564 1578
31. A. Ozerov, and E. Vincent Using the FASST source separation toolbox for noise robust speech recognition Proc. 1st Int. Workshop on Machine Listening in Multisource Environments (CHiME) Florence, Italy September 2011 pp. 86-87
32. A. Ozerov, E. Vincent, and F. Bimbot A general flexible framework for the handling of prior information in audio source separation IEEE Transactions on Audio, Speech and Language Processing 20 4 2012 1118 1133
33. L. Rabiner A tutorial on hidden Markov models and selected applications in speech recognition Proceedings of the IEEE 77 2 1989 257 286
34. D. Reynolds Large population speaker identification using clean and telephone speech IEEE Signal Processing Letters 2 3 1995 46 48
35. G. Sanguinetti, M. Milo, M. Rattray, and N.D. Lawrence Accounting for probe-level noise in principal component analysis of microarray data Bioinformatics 21 19 2005 3748 3754
36. Y. Shao, S. Srinivasan, Z. Jin, and D. Wang A computational auditory scene analysis system for speech segregation and robust speech recognition Computer Speech & Language 24 1 2010 77 93
37. Slaney, M., 1998. Auditory toolbox version 2. Tech. rep., Interval Research Corporation.
38. S. Srinivasan, and D. Wang Transforming binary uncertainties for robust speech recognition IEEE Transactions on Audio, Speech and Language Processing 15 7 2007 2130 2140
39. E. Vincent, S. Araki, F.J. Theis, G. Nolte, P. Bofill, H. Sawada, A. Ozerov, B.V. Gowreesunker, D. Lutter, and N.Q.K. Duong The signal separation evaluation campaign (2007-2010): achievements and remaining challenges Signal Processing 92 8 2012 1928 1936
40. R.F. Woolson, and W.R. Clarke Statistical Methods for the Analysis of Biomedical Data 2nd ed. 2002 Wiley-Interscience New York