Parallel feature generation based on maximizing normalized acoustic likelihood

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 953-956

  Li, Xiang ^a   Stern, Richard M ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LINEAR TRANSFORMATIONS; MATHEMATICAL TRANSFORMATIONS;

FEATURE GENERATION; GRADIENT ASCENT; INDIVIDUAL FEATURES; OPTIMAL LINEAR TRANSFORMATION; RECOGNITION ACCURACY; RECOGNITION SYSTEMS; RESOURCE MANAGEMENT; TRANSFORMATION MATRICES;

SPEECH RECOGNITION;

EID: 85009064363     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Fiscus, J. G., "A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)," Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, 1997.
2. Singh, R., Seltzer, M., Raj, B., and Stern, R. M, "Speech in noisy environments: robust automatic segmentation, feature extraction, and hypothesis combination", Proc. ICASSP 2001, Salt Lake City.
3. Li, X., Singh, R., and Stern, R.M. "Combining search spaces of heterogeneous recognizers for improved speech recognition", Proc. ICSLP 2002, Denver.
4. Li, X., and Stern, R.M., "Training of stream weights for the decoding of speech using parallel feature streams", Proc. ICASSP 2003, Hong Kong.
5. Neti, C, Potamianos, G, Luettin, J., Matthews, I., Glotin, H., and Vergyri, D, "Large-vocabulary audio-visual speech recognition: a summary of the Johns Hopkins summer 2000 workshop", IEEE Fourth Workshop on Multimedia Signal Processing, pp. 619-624, 2001
6. Ellis, D.P.W., and Bilmes, J., "Using mutual information to design feature combinations", Proc. ICSLP2000, Oct. Beijing, 2000
7. Billa, J., Colhurst, T., El-Jaroudi, A., Iyer, R., Ma, K., Matsoukas, S., Quillen, C, Richardson, F., Siu, M., Zavaliagkos, G, Gish, H., "Recent experiments in large vocabulary conversational speech recognition", Proc. ICASSP 1999, Phoenix.
8. Halberstadt, A.K. "Heterogeneous acoustic measurements and multiple classifiers for speech recognition", Ph.D. Thesis, MIT, 1998.
9. Bourlard, H., and Dupont, S., "A new ASR approach based on independent processing and recombination of partial frequency bands", Proc. ICSLP 1996, Philadelphia.
10. Hermansky, H., Tibrewala, S., and Pavel, M., "Toward ASR on partially corrupted speech", Proc. ICSLP1996, Philadelphia.
11. Li, X. and Stern, R. M. "Feature generation based on maximum classification probability for improved speech recognition", Proc. Eurospeech2003, Geneva.
12. Li, X. and Stern, R.M. "Feature generation based on maximum normalized acoustic likelihood for improved speech recognition", Proc. ICASSP 2004, Montreal.
13. Gillick, L., Cox, S.J., "Some statistical issues in speech recognition algorithms", Proc. ICASSP 1989, Glasgow.