Unsupervised Data-Driven Feature Vector Normalization With Acoustic Model Adaptation for Robust Speech Recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 2, 2010, Pages 296-309

  Buera, Luis ^a   Miguel, Antonio ^b   Saz, Óscar ^b   Ortega, Alfonso ^b   Lleida, Eduardo ^b  

^a TOSHIBA CORPORATION   (Japan)

^b UNIVERSITY OF ZARAGOZA   (Spain)

Author keywords

Acoustic model adaptation; data driven feature vector normalization; linear transformation matrices; robust speech recognition; unsupervised

Indexed keywords

EID: 85008564998     PISSN: 15587916     EISSN: 15587924     Source Type: Journal    
DOI: 10.1109/TASL.2009.2026441     Document Type: Article

References (28)

1. Y. Gong “Speech recognition in noisy environments: A survey,” Speech Commun., vol. 3, no. 16, pp. 261–291, 1995.
2. R. M. Stern, B. Raj, and P. J. Moreno, “Compensation for environmental degradation in automatic speech recognition,” in Proc. ESCA Tutorial Research Workshop Robust Speech Recognition for Unknown Communication Channels, Pont-au-Mousson, France, Apr. 1997, pp. 33–42.
3. N. Hanai and R. M. Stern, “Robust speech recognition in the automobile,” in Proc. ICSLP, Yokohama, Japan, Sep. 1994, pp. 1339–1342.
4. U. Yapanel, X. Zhang, and J. Hansen, “High performance digit recognition in real car environments,” in Proc. ICSLP, Denver, CO, Sep. 2002, pp. 793–796.
5. H. Hermansky and N. Morgan “RASTA processing for speech,” IEEE Trans. Speech Audio Process., vol. 2, no. 4, pp. 578–589, Oct. 1994.
6. D. Y. Kim, C. K. Un, and N. S. Kim “Speech recognition in noisy environments using first-order vector Taylor series,” IEEE Trans. Signal Process., vol. 5, no. 3, pp. 57–59, Mar. 1998.
7. A. Acero, “Acoustical and environmental robustness in automatic speech recognition,” Ph.D. dissertation, Elect. Comput. Eng. Dept., Carnegie Mellon Univ., Pittsburgh, PA, Sep. 1990.
8. S. F. Boll “Suppression of acoustic noise in speech using spectral subtraction,” IEEE Trans. Acoust., Speech, Signal Process., vol. 27, no. 2, pp. 113–120, Apr. 1979.
9. P. Moreno, “Speech recognition in noisy environments,” Ph.D. dissertation, Elect. Comput. Eng. Dept., Carnegie-Mellon Univ., Apr. 1996.
10. L. Buera, E. Lleida, A. Miguel, A. Ortega, and O. Saz, “Cepstral vector normalization based on stereo data for robust speech recognition,” IEEE Trans. Speech Audio Process., vol. 15, no. 3, pp. 1098–1113, Mar. 2007.
11. J. Droppo, L. Deng, and A. Acero, “Evaluation of the SPLICE algorithm on the AURORA2 database,” in Proc. Eurospeech, Aalborg, Denmark, 2001, pp. 217–220.
12. L. Neumeyer and M. Weintraub, “Probabilistic optimum filtering for robust speech recognition,” in Proc. ICASSP, Adelaide, Australia, Apr. 1994, vol. 1, pp. 417–420.
13. L. Neumeyer and M. Weintraub, “Robust speech recognition in noise using adaptation and mapping techniques,” in Proc. ICASSP, Detroit, MI, May 1995, vol. 1, pp. 141–144.
14. M. Padmanabhan, G. Saon, and G. Zweig, “Lattice-based unsupervised MLLR for speaker adaptation,” in Proc. ASR, 2000, vol. 2, pp. 128–132.
15. L. Buera, E. Lleida, J. Nolazco, A. Miguel, and A. Ortega, “Time-dependent cross-probability model for multi-environment model based linear normalization,” in Proc. ICSLP, Sep. 2006, pp. 1555–1558.
16. A. Miguel, E. Lleida, A. Juan, L. Buera, A. Ortega, and O. Saz, “Local transformation models for speech recognition,” in Proc. ICSLP, Pittsburgh, PA, 2006, pp. 1598–1601.
17. S. Molau, “Normalization in the acoustic feature space for improved speech recognition,” Ph.D. dissertation, Univ. of Aachen, Aachen, Germany, Feb. 2003.
18. A. Moreno, B. Lindberg, C. Draxler, G. Richard, K. Choukri, S. Euler, and J. Allen, “Speechdat-car. A large speech database for automotive environments,” in Proc. LREC, Athens, Greece, 2000, vol. 2, pp. 895–900.
19. H. van den Heuvel, J. Boudy, R. Comeyne, S. Euler, A. Moreno, and G. Richard, “The speechdat-car multilingual speech databases for in-car applications: Some first validation results,” in Proc. Eurospeech, Budapest, Hungary, Sep. 1999, vol. 5, pp. 2279–2282.
20. H. G. Hirsch and D. Pearce, “The aurora experimental framework for the performance evaluations of speech recognition systems under noisy conditions,” in Proc. ISCA ITRW ASR2000, Paris, France, Sep. 2000, pp. 29–32.
21. A. P. Dempster, N. Laird, and D. Rubin “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Statist. Soc., vol. 9, no. 1, pp. 1–37, 1977.
22. P. Moreno, “Speech Recognition in Noisy Environments,” Ph.D. dissertation, Elect. Comput. Eng. Dept., Carnegie Mellon Univ., Pittsburgh, PA, Apr. 1996.
23. J. Droppo, L. Deng, and A. Acero, “Evaluation of the splice algorithm on the Aurora2 database,” in Proc. Eurospeech, Sep. 2001, vol. 1, pp. 217–220.
24. A. P. Varga and R. K. Moore, “Hidden Markov model decomposition of speech and noise,” in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 1990, pp. 845–848.
25. ETSI, “Speech processing transmission and quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms,” Apr. 2000, ETSI ES 201 108 version 1.1.2, Tech. Rep.
26. ETSI, “Speech processing, transmission and quality aspects (STQ); Distributed speech recognition; Advanced front-end feature extraction algorithm; Compression algorithms,” Oct. 2002, ETSI ES 202 050 version 1.1.1, Tech. Rep.
27. H. Ney and S. Ortmanns “Dynamic programming search for continuous speech recognition,” IEEE Signal Process. Mag., vol. 16, no. 5, pp. 64–83, Sep. 1999.
28. S. Young, G. Evermann, M. Gales, T. Hain, D. Tershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woolland, The “HTK Book (for HTK Version 3.3),” Cambridge Univ. Eng. Dept., Apr. 2005.