Minimum phoneme error based heteroscedastic linear discriminant analysis for speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn I, Issue , 2005, Pages

  Zhang, Bing ^a,b   Matsoukas, Spyros ^a  

^a BBN TECHNOLOGIES   (United States)

^b Northeastern University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BROADCASTING; ERROR ANALYSIS; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH ANALYSIS;

HIDDEN MARKOV MODELS; MINIMUM PHONEME ERROR; RECOGNITION ACCURACY; TRAINING FRAMEWORKS;

SPEECH RECOGNITION;

EID: 33646793688     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415266     Document Type: Conference Paper

References (8)

1. G. Saon et al., "Maximum likelihood discriminant feature spaces," in Proceedings of ICASSP, June 2000, vol. 2, pp. II1 129-II1 132.
2. N. Kumar and A. G. Andreou, "A generalization of linear discriminant analysis in maximum likelihood framework," Tech. Rep. JHU-CLSP Technical Report No. 16, Johns Hopkins University, Aug. 1996.
3. M. J. F. Gales, "Maximum likelihood multiple subspace projections for hidden markov models," IEEE Transactions on Speech and Audio Processing, vol. 10, no. 2, pp. 37-47, Feb. 2002.
4. V. Valtchev et al., "MMIE training of large vocabulary recognition systems," Speech Communication 22, pp. 303-314, June 1997.
5. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proceedings of ICASSP, 2002.
6. X. Liu and M. J. F. Gales, "Discriminative training of multiple subspace projections for large vocabulary speech recognition," Tech. Rep. CU Technical Report No. 489, Cambridge University, England, Aug. 2004.
7. S. Matsoukas and R. Schwartz, "Improved speaker adaptation using speaker dependent feature projections," in Proceedings of ASRU, Virgin Islands, U.S., Nov. 2003, pp. 273-278.
8. R. Schwartz et al., "Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system," in Proceedings of ICASSP, Montreal, Quebec, Canada, May 2004, vol. III, pp. 753-756.