Connectionist Probability Estimation in HMM Speech Recognition

TitleConnectionist Probability Estimation in HMM Speech Recognition
Publication TypeTechnical Report
Year of Publication1992
AuthorsRenals, S., & Morgan N.
Other Numbers786
Abstract

This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical understanding of connectionist networks as probability estimators, first elucidated by Hervé Bourlard. We review the basis of HMM speech recognition, and point out the possible benefits of incorporating connectionist networks. We discuss some issues necessary to the construction of a connectionist HMM recognition system, and describe the performance of such a system, including evaluations on the DARPA database, in collaboration with Mike Cohen and Horacio Franco of SRI International. In conclusion, we show that a connectionist component improves a state of the art HMM system.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1992/tr-92-081.pdf
Bibliographic Notes

ICSI Technical Report TR-92-081

Abbreviated Authors

S. Renals and N. Morgan

ICSI Publication Type

Technical Report