Ashutosh Garg, Gerasimos Potamianos, et al.
ICASSP 2003
In this paper, we propose a new fast and flexible algorithm based on the maximum entropy (MAXENT) criterion to estimate stream weights in a state-synchronous multi-stream HMM. The technique is compared to the minimum classification error (MCE) criterion and to a brute-force, grid-search optimization of the WER on both a small and a large vocabulary audio-visual continuous speech recognition task. When estimating global stream weights, the MAXENT approach gives comparable results to the grid-search and the MCE. Estimation of state dependent weights is also considered: We observe significant improvements in both the MAXENT and MCE criteria, which, however, do not result in significant WER gains.
Ashutosh Garg, Gerasimos Potamianos, et al.
ICASSP 2003
Scott Axelrod
ICASSP 2002
Gerasimos Potamianos, Chalapathy Neti
INTERSPEECH - Eurospeech 2003
Brian Kingsbury, Lidia Mangu, et al.
INTERSPEECH - Eurospeech 2003