The integration of principal component analysis and cepstral mean subtraction in parallel model combination for robust speech recognition

Digital Signal Processing: A Review Journal

Volumn 21, Issue 1, 2011, Pages 36-53

  Veisi, Hadi ^a   Sameti, Hossein ^a  

^a SHARIF UNIVERSITY OF TECHNOLOGY   (Iran)

Author keywords

Automatic speech recognition; Cepstral mean subtraction (CMS); Parallel model combination (PMC); PCA CMS based PMC (PC PMC); Principal component analysis (PCA); Robustness

Indexed keywords

ADDITIVE NOISE; CONTINUOUS SPEECH RECOGNITION; CONVOLUTION; COVARIANCE MATRIX; MAXIMUM LIKELIHOOD; ROBUSTNESS (CONTROL SYSTEMS); SPEECH;

ADAPTATION TECHNIQUES; AUTOMATIC SPEECH RECOGNITION; CEPSTRAL MEAN SUBTRACTION; FEATURE COMPENSATION; MAXIMUM LIKELIHOOD LINEAR REGRESSION; PARALLEL MODEL COMBINATIONS; PCA-CMS BASED PMC (PC-PMC); ROBUST SPEECH RECOGNITION;

PRINCIPAL COMPONENT ANALYSIS;

EID: 78649946011     PISSN: 10512004     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.dsp.2010.07.004     Document Type: Article

References (73)

1. M.J.F. Gales, Model-based techniques for noise robust speech recognition, Ph.D. thesis, University of Cambridge, September 1995.
2. H. Veisi, Model-based methods for noise robust speech recognition systems, M.S. thesis, Computer Engineering Department, Sharif University of Technology, Tehran, Iran, November 2005.
3. H. Veisi, H. Sameti, H.R. Abutalebi, On the using of principal component analysis on the Farsi continuous speech recognition for feature robustness and feature reductions, in: Annual Computer Society of Iran Computer Conference (CSICC'05), Tehran, Iran, 2005, pp. 242-251.
4. H. Hermansky, RASTA-PLP speech analysis, ICSI technical report TR-91069, International Computer Science Institute, Berkeley, CA, 1991.
5. P.J. Moreno, Speech recognition in noisy environments, Ph.D. thesis, Carnegie Mellon University, 1996.
6. J. Droppo, L. Deng, A. Acero, Evaluation of SPLICE on the Aurora 2 and 3 tasks, in: Proc. Int. Conf. on Spoken Language Processing (ICSLP'02), Colorado, September 2002, pp. 217-220.
7. V. Stouten, H. Van Hamme, P. Wambacq, Joint removal of additive and convolutional noise with model-based feature enhancement, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'04), 2004, pp. 949-952.
8. A. Sasou, T. Tanaka, S. Nakamura, F. Asano, HMM-based feature compensation methods: an evaluation using the Aurora2, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'04), 2004, pp. 121-124.
9. W. Kim, and J.H.L. Hansen Feature compensation in the cepstral domain employing model combination Speech Comm. 51 2 2009 83 96
10. J. Barker, M. Cooke, P. Green, Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise, in: Eur. Conf. on Speech Communication and Technology (Eurospeech'01), 2001, pp. 213-216.
11. M. Cook, P. Green, L. Josifovski, and A. Vizinho Robust automatic speech recognition with missing and unreliable acoustic data Speech Comm. 34 3 2001 267 285
12. B. Raj, M.L. Seltzer, and R.M. Stern Reconstruction of missing features for robust speech recognition Speech Comm. 34 4 2004 275 296
13. H. Veisi, H. Sameti, B. Babaali, K. Hosseinzadeh, M.T. Manzuri, Improving the robustness of Persian large vocabulary continuous speech recognition system for real applications, in: IEEE Int. Conf. on Information and Communication Technologies (ICTTA'06), Umayyad Palace, Damascus, Syria, 2006, pp. 1293-1297.
14. P. Zhan, M. Westphal, M. Finke, A. Waibel, Speaker normalization and speaker adaptation-A combination for conversational speech recognition, in: Eur. Conf. on Speech Communication and Technology (EUROSPEECH'97), Rhodes, Greece, 1997, pp. 2087-2090.
15. L. Welling, H. Ney, and S. Kanthak Speaker adaptive modeling by vocal tract normalization IEEE Trans. Speech Audio Process. 10 2002 415 426
16. M.J.F. Gales, S. Young, An improved approach to the Hidden Markov model decomposition of speech and noise, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'92), San Francisco, CA, USA, 1992, pp. 233-236.
17. M.J.F. Gales, and S.J. Young Cepstral parameter compensation for HMM recognition in noise Speech Comm. 12 1993 231 239
18. C.J. Leggetter, and P.C. Woodland Maximum likelihood linear regression for speaker adaptation of continuous density Hidden Markov models Comp. Speech Language 9 1995 171 185
19. M.J.F. Gales, and P.C. Woodland Mean and variance adaptation within the MLLR framework Comp. Speech Language 10 1996 249 264
20. K. Hosseinzadeh, Improving the accuracy of continuous speech recognition in noisy environments, M.S. thesis, Computer Engineering Department, Sharif University of Technology, Tehran, Iran, November 2004.
21. K. Hosseinzadeh, H. Sameti, H.R. Abutalebi, A. Fazel Dehkordi, MLLR method for environmental adaptation in the continuous FARSI speech recognition, in: Conf. on Intelligent Systems, Kerman, Iran, 2004.
22. D. Pye, P.C. Woodland, Experiments in speaker normalization and adaptation for large vocabulary speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASS0P'97), Munich, Germany, 1997, pp. 1047-1050.
23. P.C. Woodland, Speaker adaptation: techniques and challenges, in: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'00), 2000, pp. 85-90.
24. X. Huang, A. Acero, and H.W. Hon Spoken Language Processing: A Guide to Theory, Algorithm, and System Development 2001 Prentice-Hall PTR Upper Saddle River, NJ, USA
25. T. Kristjansson, B. Frey, L. Deng, A. Acero, Towards non-stationary model-based noise adaptation for large vocabulary speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'01), Salt Lake City, UT, USA, 2001, pp. 337-340.
26. A. Acero, L. Deng, T. Kristjansson, J. Zhang, HMM adaptation using vector Taylor series for noisy speech recognition, in: Int. Conf. on Spoken Language Processing (ICSLP'00), Beijing, China, 2000, pp. 869-872.
27. H. Liao, M.J.F. Gales, Uncertainty decoding for noise robust speech recognition, Technical report, CUED/F-INFENG/TR499, University of Cambridge, 2004.
28. H. Liao, M.J.F. Gales, Joint uncertainty decoding for noise robust speech recognition, in: 9th Eur. Conf. on Speech Communication and Technology (Eurospeech'05), Lisbon, Portugal, 2005.
29. S. Sagayama, Y. Yamaguchi, S. Takahashi, Jacobian adaptation of noisy speech models, in: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'97), Santa Barbara, CA, USA, 1997, pp. 396-403.
30. K. Parssinen, P. Salmela, M. Harju, I. Kiss, Comparing Jacobian adaptation with cepstral mean normalization and parallel model combination for noise robust speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'02), Orlando, FL, USA, 2002, pp. I-193-I-196.
31. J.R. Deller, J.G. Proakis, and J.H. Hansen Discrete Time Processing of Speech Signals 1993 Prentice-Hall PTR Upper Saddle River, NJ, USA
32. L. Rabiner, and B.H. Juang Fundamentals of Speech Recognition 1993 Prentice-Hall, Inc. Upper Saddle River, NJ, USA
33. R. Martin, Spectral subtraction based on minimum statistics, in: European Signal Processing Conference (Eusipco'94), Edinburgh, Scotland, 1994, pp. 1182-1185.
34. H.G. Hirsch, C. Ehrlicher, Noise estimation techniques for robust speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'95), Detroit, MI, USA, 1995, pp. 153-156.
35. C. Ris, and S. Dupont Assessing local noise level estimation methods: application to noise robust ASR Speech Comm. 34 1-2 2001 141 158
36. D.Y. Kim, C.K. Un, and N. S Kim Speech recognition in noisy environments using first order vector Taylor series Speech Comm. 24 1998 39 49
37. L. Deng, J. Droppo, and A. Acero Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition IEEE Trans. Speech Audio Process. 11 6 2003 568 580
38. Y. Gong A method of joint compensation of additive and convolutive distortions for speaker-independent speech recognition IEEE Trans. Speech Audio Process. 13 5 2005 975 983
39. J. Li, L. Deng, Y. Gong, A. Acero, High-performance HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series, in: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'07), Kyoto, Japan, 2007.
40. A.P. Varga, R.K. Moore, Hidden Markov model decomposition of speech and noise, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'90), Albuquerque, New Mexico, USA, 1990, pp. 845-848.
41. Y. Gong, A comparative study of approximations for parallel model combination of static and dynamic parameters, in: Int. Conf. on Spoken Language Processing (ICSLP'02), Denver, Colorado, USA, 2002, pp. 1029-1032.
42. J. Hung, J. Shen, and L. Lee New approaches for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques IEEE Trans. Speech Audio Process. 9 2001 842 855
43. M.J.F. Gales, S.J. Young, A fast and flexible implementation of parallel model combination, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'95), Detroit, MI, USA, 1995, pp. 133-136.
44. R. Yang, P. Haavisto, An improved noise compensation algorithm for speech recognition in noise, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'96), Atlanta, GA, USA, 1996, pp. 49-52.
45. H. Yamamoto, M. Yamada, T. Kosaka, Y. Komori, Y. Ohora, Independent calculation of power parameters on PMC method, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'96), Atlanta, GA, USA, 1996, pp. 41-44.
46. J. Hung, J. Shen, L. Lee, Improved parallel model combination techniques with split gaussian mixtures for speech recognition under noisy conditions, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'9), Phoenix, AZ, USA, 1999, pp. 437-440.
47. T.H. Hwang, H.C. Wang, Weighted parallel model combination for noisy speech recognition, in: Int. Conf. on Spoken Language Processing (ICSLP'98), Sydney, Australia, 1998, pp. 1527-1530.
48. J. Hung, J. Shen, L. Lee, Improved robustness for speech recognition under noisy conditions using correlated parallel model combination, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'98), Seattle, WA, USA, 1998, pp. 553-556.
49. W.T. Hong, S.H. Chen, A segment-based C0 adaptation scheme for PMC-based noisy Mandarin speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'99), Phoenix, AZ, USA, 1999, pp. 433-436.
50. R. Sarikaya, J.H.L. Hansen, PCA-PMC: a novel use of a priori knowledge for fast parallel model combination, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'00), Istanbul, Turkey, 2000, pp. II1113-II1116.
51. Y.H. Chang, Y.J. Chung, S.U. Park, Improved model parameter compensation methods for noise-robust speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'98), Seattle, WA, USA, 1998, pp. 561-564.
52. R.W. Morris, M.E. Deisher, Efficient second-order adaptation for large vocabulary distributed speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'02), Orlando, FL, USA, 2002, pp. I-205-I-208.
53. J. Kleban, Y. Gong, HMM adaptation and microphone array processing for distant speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'00), Istanbul, Turkey, 2000, pp. 1411-1414.
54. C.K. Raut, T. Nishimoto, S. Sagayama, Model composition by Lagrange polynomial approximation for robust speech recognition in noisy environment, in: Int. Conf. on Spoken Language Processing (ICSLP'04), Jeju Island, Korea, 2004.
55. P.C. Woodland, M.J.F. Gales, D. Pye, Improving environmental robustness in large vocabulary speech recognition, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'96), Atlanta, GA, USA, 1996, pp. 65-68.
56. J.A.N. Flores, S.J. Young, Continuous speech recognition in noise using spectral subtraction and HMM adaptation, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'94), Adelaide, SA, Australia, 1994, pp. I/409-I/412.
57. H. Yamamoto, T. Kosaka, M. Yamada, Y. Komori, M. Fujita, Fast speech recognition algorithm under noisy environment using modified CMS-PMC and improved IDMM+ SQ, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'97), Munich, Germany, 1997, pp. 847-850.
58. C. Cerisara, D. Fohr, Fast channel and noise compensation in the spectral domain, in: European Signal Processing Conference (EUSIPCO'02), Toulouse, France, 2002, pp. 73-76.
59. T. Kosaka, H. Yamamoto, M. Yamada, Y. Komori, Instantaneous environment adaptation techniques based on fast PMC and MAP-CMS methods, in: IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'98), Seattle, WA, USA, 1998, pp. 789-792.
60. W. Kim, S. Ahn, H. Ko, Feature compensation scheme based on parallel combined mixture model, in: European Conference on Speech Communication and Technology (Eurospeech'03), Geneva, Switzerland, 2003, pp. 677-680.
61. C. Miao, Y. Wang, A novel use of residual noise model for modified PMC, in: European Conference on Speech Communication and Technology (Eurospeech'03), Geneva, Switzerland, 2003.
62. H. Veisi, and H. Sameti The combination of CMS with PMC for improving the robustness of speech recognition systems Annual Computer Society of Iran Computer Conference (CSICC'08) Kish Island, Iran, 2008 2008 Springer-Verlag
63. A. Papoulis, and S.U. Pillai Probability, Random Variables, and Stochastic Processes 2002 McGraw-Hill New York
64. H. Sameti, H. Veisi, M. Bahrani, B. Babaali, and K. Hosseinzadeh Nevisa, a Persian continuous speech recognition system Annual Computer Society of Iran Computer Conference (CSICC'08) Kish Island, Iran, 2008 2008 Springer-Verlag
65. M. Bijankhan, J. Seikhzadeghan, M.R. Roohani, Y. Samareh, K. Lucas, M. Tebyani, FARSDAT-the speech database of Farsi spoken language, in: Int. Conf. on Speech Science and Technology (SST'94), Perth, Australia, 1994, pp. 826-831.
66. M. Berouti, R. Schwartz, J. Makhoul, Enhancement of speech corrupted by acoustic noise, in: Proceeding of the IEEE Conference on Acoustics, Speech and Signal Processing (ICASSP'79), 1979, pp. 208-211.
67. Y. Ephraim, and I. Cohen Recent advancements in speech enhancement The Electrical Engineering Handbook 2006 CRC Press 12 26 Chap. 15
68. Y. Hu, and P. Loizou A comparative intelligibility study of single-microphone noise reduction algorithms J. Acoust. Soc. Amer. 122 3 2007 1777 1786 (Pubitemid 47560539)
69. P.C. Woodland, D. Pye, M.J.F. Gales, Iterative unsupervised adaptation using maximum likelihood linear regression, in: Int. Conf. on Spoken Language Processing (ICSLP'96), vol. 2, Philadelphia, PA, US, 3-6 October 1996, pp. 1133-1136.
70. M. Pitz, F. Wessel, H. Ney, Improved MLLR speaker adaptation using confidence measures for conversational speech recognition, in: Int. Conf. on Spoken Language Processing (ICSLP'00), Beijing, China, 2000.
71. K.Y. Kwan, T. Lee, C. Yang, Unsupervised N-best based model adaptation using model-level confidence measures, in: Int. Conf. on Spoken Language Processing (ICSLP'02), 2002, pp. 69-72.
72. S.C. Jou, T. Schultz, A. Waibel, Adaptation for soft whisper recognition using a throat microphone, in: Proc. Int. Conf. on Speech and Language Processing (ICSLP'04), Jeju Island, Korea, October 2004.
73. D.K. Kim, M.J.F. Gales, Noisy CMLLR for noise-robust speech recognition, CUED technical report CUED/F-INFENG/TR611, University of Cambridge, 2009.