A training procedure for verifying string hypotheses in continuous speech recognition
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 281-284
- https://doi.org/10.1109/icassp.1995.479528
Abstract
A procedure is proposed for verifying the occurrence of string hypotheses produced by a hidden Markov model (HMM) based continuous speech recognizer. Most existing procedures verify word hypotheses through likelihood ratio scoring procedures computed using ad hoc approximations for the density of the alternative hypothesis in the denominator of the likelihood ratio statistic. The discriminative training procedure described in this paper attempts to adjust the parameters of the null hypothesis and the alternate hypothesis models to increase the power of a hypothesis test for utterance verification. The training procedure was evaluated for its ability to detect a twenty word vocabulary in a subset of the Switchboard conversational speech corpus. Experimental results show that the use of this procedure results in significant improvement in the word verification operating characteristic, as well as an improvement in the overall system performance.Keywords
This publication has 7 references indexed in Scilit:
- A hidden Markov model based keyword recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An N-best candidates-based discriminative training for speech recognition applicationsIEEE Transactions on Speech and Audio Processing, 1994
- A two pass classifier for utterance rejection in keyword spottingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Hybrid neural-network/HMM approaches to wordspottingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Discriminative learning for minimum error classification (pattern recognition)IEEE Transactions on Signal Processing, 1992
- Discriminant wordspotting techniques for rejecting non-vocabulary utterances in unconstrained speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Automatic modeling for adding new words to a large-vocabulary continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991