Analysis and comparison of two speech feature extraction/compensation algorithms

IEEE Signal Processing Letters

Volumn 12, Issue 6, 2005, Pages 477-480

  Deng, Li ^a   Wu, Jian ^b   Droppo, Jasha ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

^b MICROSOFT   (United States)

Author keywords

Discriminative training; Feature compensation; Feature extraction; Hidden Markov model; Minimum classification error; Minimum phone error; Piecewise linear mapping; Posterior probability; Speech processing

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; ERROR ANALYSIS; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; MATRIX ALGEBRA; OPTIMIZATION; PROBABILITY; SPEECH PROCESSING; SPURIOUS SIGNAL NOISE; VECTORS;

DISCRIMINATIVE TRAINING; FEATURE COMPENSATION; HIDDEN MARKOV MODEL; MINIMUM CLASSIFICATION ERROR; MINIMUM PHONE ERROR; PIECEWISE LINEAR MAPPING; POSTERIOR PROBABILITY;

SPEECH RECOGNITION;

EID: 20444414457     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/LSP.2005.847861     Document Type: Article

References (16)

1. L. Deng, A. Acero, M. Plumpe, and X. D. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," in Proc. Int. Conf. Spoken Lang. Process., vol. III, Oct. 2000, pp. 806-809.
2. L. Deng, A. Acero, L. Jiang, J. Droppo, and X. D. Huang, "High-performance robust speech recognition using stereo training data," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., vol. I, Salt Lake City, UT, Apr. 2001, pp. 301-304.
3. 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., vol. 11, no. 6, pp. 568-580, Nov. 2003.
4. J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the Aurora2 database," in Proc. Eur. Conf. Speech Commun. Technol., vol. 1, Aalborg, Denmark, Sep. 2001, pp. 217-220.
5. J. Droppo, A. Acero, and L. Deng, "Uncertainty decoding with SPLICE for noise robust speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., vol. I, Orlando, FL, May 2002, pp. 57-60.
6. P. Moreno, B. Raj, and R. Stern, "A vector Taylor series approach for environment-independent speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Munich, Germany, 1996, pp. 733-736.
7. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. IEEE Int. Conf. Acoust,, Speech, Signal Process., vol. I, Orlando, FL, May 2002, pp. 105-108.
8. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," in Proc. DARPA EARS RT-04 Workshop, Palisades, NY, 2004, Paper no. 35.
9. L. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
10. M. Rahim, B.-H. Juang, W. Chou, and E. Buhrke, "Signal conditioning techniques for robust speech recognition," IEEE Signal Process. Lett., vol. 3, no. 4, pp. 107-109, Apr. 1996.
11. A. Sankar and C.-H. Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Process., vol. 4, no. 3, pp. 190-202, May 1996.
12. J. Wu, "Discriminative speaker adaptation and environmental robustness in automatic speech recognition," Ph.D. dissertation, Univ. of Hong Kong, 2004.
13. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach and its evaluation on Aurora2 database," in Proc. Int. Conf. Spoken Lang. Process., Denver, CO, pp. 453-456.
14. J. Wu and Q. Huo, "An environment compensated maximum likelihood training approach based on stochastic vector mapping," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., vol. 1, Philadelphia, PA, Mar. 2005, pp. 429-432.
15. J. Wu and Q. Huo, "Several HKU approaches to robust speech recognition and their evaluation on Aurora connected digit recognition tasks," in Proc. Eur. Conf. Speech Commun. Technol., vol. I, Geneva, Switzerland, Sep. 2003, pp. 21-24.
16. Q. Zhu, B. Chen, N. Morgan, and A. Stolcke, "On using MLP features in LVCSR," in Proc. Int. Conf. Spoken Lang. Process., Jeju Island, Korea, Oct. 2004, pp. 554-557.