Stereo-based stochastic mapping for robust speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 17, Issue 7, 2009, Pages 1325-1334

  Afify, Mohamed ^a   Cui, Xiaodong ^b   Gao, Yuqing ^b  

^a Orange Lab   (Egypt)

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Noise robustness; Nonlinear mapping; Speech recognition; Stereo data

Indexed keywords

CLEAN SPEECH; DIGIT RECOGNITION; FIELD DATA; GAUSSIAN MIXTURE MODEL; JOINT DISTRIBUTIONS; LARGE VOCABULARY; LINEAR TRANSFORM; LINEAR TRANSFORMATION; MAXIMUM A POSTERIORI CRITERIONS; MINIMUM MEAN SQUARE ERROR CRITERION; NOISE ROBUSTNESS; NONLINEAR MAPPING; REAL ENVIRONMENTS; ROBUST SPEECH RECOGNITION; STEREO-BASED; STEREO-DATA; STOCHASTIC MAPPING; WORD ERROR RATE;

ACOUSTIC NOISE; ERROR COMPENSATION; MAPPING; MATHEMATICAL TRANSFORMATIONS;

SPEECH RECOGNITION;

EID: 68549125183     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2009.2018017     Document Type: Article

References (37)

1. A. Acero, "Acoustical and environmental robustness for automatic speech recognition," Ph.D. dissertation, Elect. Comput. Eng. Dept., Carnegie Mellon Univ., Pittsburgh, PA, Sep. 1990.
2. M. Afify, X. Cui, and Y. Gao, "Stereo-based stochastic mapping for robust speech recognition," in Proc. ICASSP'07, Honolulu, hi, Apr. 2007, pp. 377-380.
3. M. Afify, "Accurate compensation in the log-spectral domain for noisy speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 388-398, May 2005.
4. H. Bourlard and S. Dupont, "Subband-based speech recognition," in Proc. ICASSP'97, Munich, Germany, Apr. 1997, pp. 1251-1254.
5. X. Cui, M. Afify, and Y. Gao, "N-best based stochastic mapping on stereo HMM for noise robust speech recognition," in Proc. Interspeech'08, Brisbane, Australia, Sep. 2008.
6. V. Digalakis, D. Rtischev, and L. Neumeyer, "Speaker adaptation by constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol. 3, no. 5, pp. 357-366, Sep. 1995.
7. J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the AURORA 2 database," in Proc. Eurospeech'01, Aalborg, Denmark, Sep. 2001.
8. J. Droppo, L. Deng, and A. Acero, "Uncertainty decoding with splice for noise robust speech recognition," in Proc. ICASSP'02, Orlando, FL, May 2002, pp. 57-80.
9. B. Frey, L. Deng, A. Acero, and T. Kristjanson, "ALGONQUIN: Iterating laplace's method to remove multiple types of acoustic distortion for robust speech recognition," in Proc. Eurospeech'01, Aalborg, Denmark, Sep. 2001.
10. M. Gales and S. Young, "Robust continuous speech recognition using parallel model combination," IEEE Trans. Speech Audio Process., vol. 4, no. 5, pp. 352-359, Sep. 1996.
11. M. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., pp. 193-228, 1998.
12. M. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Trans. Speech Audio Process., vol. 7, no. 3, pp. 272-281, May 1999.
13. Y. Gao, B. Zhou, L. Gu, R. Sarikaya, H.-K. Kuo., A.-V.I. Rosti, M. Afify, and W. Zhu, "IBM MASTOR: Multilingual automatic speech-to-speech translator," in Proc. ICASSP'06, Tolouse, France, 2006, pp. 1205, 1208.
14. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, Apr. 1995.
15. J. Hershey, T.Kristjansson, and Z. Zhang, "Model-based fusion ofbone and air sensors for speech enhancement and robust speech recognition," in Proc. ISCA Workshop Statist. Percept. Audio Process., 2004.
16. X. Huang, A. Acero, and H. Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Upper Saddle River, NJ: Prentice-Hall, 2001.
17. Q. Huo and D. Zhu, "A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations," in Proc. Interspeech'06, Pittsburgh, PA, Sep. 2006.
18. B. H. Juang and L. R. Rabiner, "Signal restoration by spectral mapping," in Proc. ICASSP'87, Apr. 1987, pp. 2368-2372.
19. S. Kozat, K. Visweswariah, andR. Gopinath, "Feature adaptation based on Gaussian posteriors," in Proc. ICASSP'06, Tolouse, France, Apr. 2006, pp. 221-224.
20. T. Kristjansson and B. Frey, "Accounting for uncertainity in observations: A new paradigm for robust speech recognition," in Proc. ICASSP'02, Orlando, FL, May 2002.
21. C. H. Lee, "On stochastic feature and model compensation approaches to robust speech recognition," Speech Commun., vol. 25, pp. 29-47, 1998.
22. C. H. Lee and Q. Huo, "On adaptive decision rules and decision parameter adaptation for automatic speech recognition," Proc. IEEE, vol. 88, no. 8, pp. 1241-1269, Aug. 2000.
23. C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, pp. 171-185, 1995.
24. J. Li, L. Deng, Y.Gong, and A. Acero, "High performance HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series," in Proc. ASRU'07, Kyoto, Japan, 2007.
25. H. Liao and M. Gales, "Adaptive training with joint uncertainty decoding for robust recognition of noisy data," in Proc. ICASSP'07, Honolulu, HI, Apr. 2007, pp. 389-392.
26. H. Liao and M. Gales, "Joint uncertainity decoding for noise robust speech recognition," in Proc. Eurospeech'05, Lisbone, Portugal, Sep. 2005.
27. R. Lippmann, E. Martin, and D. Paul, "Multi-style training for robust isolated-word recognition," in Proc. DARPA Speech Recognition Workshop, Mar. 24-26, 1987, pp. 96-99.
28. C. Mokbel and G. Chollet, "Word recognition in the car: Speech enhancement/spectral transformations," in Proc. ICASSP'91, Toronto, 1991, pp. 925-928.
29. P. J. Moreno, B. Raj, and R. M. Stern, "A vector taylor series approach for environment-independent speech recognition," in Proc. ICASSP, Atlanta, GA, May 1996, pp. 733-736.
30. L. Neumeyer and M. Weintraub, "Probabilistic optimal filtering for robust speech recognition," in Proc. ICASSP'94, Adelaide, Australia, Apr. 1994, pp. 417-420.
31. M. K. Omar, personal communication, May 2004.
32. A. Potamianos and P. Maragos, "Time-frequency distributions for automatic speech recognition," IEEE Trans. Speech Audio Process., vol. 9, pp. 196-200, Mar. 2001.
33. G. Saon, G. Zweig, and M. Padmanabhan, "Linear feature space projections for speaker adaptation," in Proc. ICASSP'01, Salt lake City, UT, Apr. 2001, pp. 325-328.
34. V. Stouten, H. Van Hamme, and P. Wambacq, "Accounting for the uncertainity of speech estimates in the context of model-based feature enhancement," in Proc. ICSLP'04, Jeju, Korea, Sep. 2004.
35. Y. Stylianou, O. Cappe, and E. Moulines, "Continuous probabilistic transform for voice conversion," IEEE Trans. Speech Audio Process., vol. 6, pp. 131-142, Jan. 1998.
36. K. Visweswariah and P. Olsen, "Feature adaptation using projection of Gaussian posteriors," in Proc. Interspeech'05, Lisbone, Portugal, Sep. 2005.
37. S. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK book (for HTK Version 3.1). Dec. 2001.