Learning state-dependent stream weights for multi-codebook HMM speech recognition systems

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

Volumn 1, Issue , 1994, Pages I217-I220

  Rogina, I ^a   Waibel, A ^a  

^a UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING ALGORITHMS; SIGNAL PROCESSING;

CEPSTRAL COEFFICIENTS; CONTEXT DEPENDENT; MULTIPLE INFORMATION STREAMS; POWER COEFFICIENTS; PROBABILITY ESTIMATOR; SPEECH RECOGNITION SYSTEMS; SPEECH RECOGNIZER; STATE-DEPENDENT;

SPEECH RECOGNITION;

EID: 85057282838     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389316     Document Type: Conference Paper

References (7)

1. E.L Bocxhieri and J.G. Wilpon, "Discrim-inative feature selection for speech recognition", Computer Speech and Language, Vol. 7, pp. 229-246 (1993)
2. Huang, X., Alleva, F., Hayamizu, S., Hon 1 H., Hwang, M., and Lee, K., "The SPH1NX-II Speech Recognition System", Technical Report S-92-112, Carnegie Mellon University, 1992
3. K.F. Lee, "Large Vocabulary Speaker-in-dependent Continuous Speech Recognition: The Sphinx System", PhD Thesis, Carnegie Mellon University, April 18, 1988, Report CMU-CS-88-148
4. Shikano, K., "Evaluation of LPC Spec-tral Matching Measures for Phonetic Unit Recog-nition", Technical Report, Computer Science De-partment, Carnegie Mellon University, 1986
5. Otto Schmidbauer, Joe Tebelskis, "An LVQ based Reference Model for Speaker-Adaptive Speech Recognition", ICASSP 92, Vol. I, pp. 441-444
6. Alex Waibel et al., "JANUS: A Speech to Speech Translation System Using Connection-ist and Symbolic Processing Strategies", ICASSP 91, Vol. II, pp. 793-796
7. Cindy Wood, "The Conference Registra-tion Task", Technical Report, Computer Science Department, Carnegie Mellon University, 1991