Bayesian model combination (BAYCOM) for improved recognition

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

Volumn I, Issue , 2005, Pages

  Sankar, Ananth ^a  

^a NUANCE COMMUNICATIONS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC DEVICES; DECISION THEORY; MATHEMATICAL MODELS;

BAYESIAN MODEL COMBINATION; COMBINATION METHODS; RECOGNITION EXPERIMENTS; UTTERANCE REJECTION;

SPEECH RECOGNITION;

EID: 33646757234     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415246     Document Type: Conference Paper

References (6)

1. J.G. Fiscus, "A Post-Processing System to Yield Reduced Word Error Rates: Recognizer Output Voting Error Reduction (ROVER)," in Proc. ASRU, December 1997, pp. 347-354.
2. A. Stolcke, et al., "The SRI March 2000 Hub-5 Conversational Speech Transcription System," in Proc. Speech Transcription Workshop, 2000.
3. G. Evermann and P.C. Woodland, "Posterior Probability Decoding, Confidence Estimation, and System Combination," in Proc. Speech Transcription Workshop, 2000.
4. Y. Freund and R.E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of Comp. and Sys. Sciences, vol. 55, no. 1, pp. 119-139, August 1997.
5. V. Digalakis, P. Monaco, and H. Murveit, "Genones: Generalized Mixture Tying in Continuous Hidden Markov Model-Based Speech Recognizers," IEEE Trans. on Speech and Audio Processing, vol. 4, no. 4, pp. 281-289, 1996.
6. E. Chang, "Improving Rejection with Semantic Slot-Based Confidence Scores," in Proceedings of EUROSPEECH, 1999, pp. 271-274.