Kapadia, S and Valtchev, V and Young, SJ (1993) MMI training for continuous phoneme recognition on the TIMIT database. Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, 2. ISSN 0736-7791Full text not available from this repository.
This paper reports our experiences with a phoneme recognition system for the TIMIT database which uses multiple mixture continuous density monophone HMMs trained using MMI. A comprehensive set of results are presented comparing the ML and MMI training criteria for both diagonal and full covariance models. These results using simple monophone HMMs show clear performance gains achieved by MMI training, and are comparable to the best reported by others including those which use context-dependent models. In addition, the paper discusses a number of performance and implementation issues which are crucial to successful MMI training.
|Divisions:||Div F > Machine Intelligence|
|Depositing User:||Cron Job|
|Date Deposited:||09 Dec 2016 17:56|
|Last Modified:||29 Apr 2017 01:38|