Details

Autor(en) / Beteiligte

• Gravier, Guillaume
• Axelrod, Scott
• Potamianos, Gerasimos
• Neti, Chalapathy

Titel

Maximum entropy and MCE based HMM stream weight estimation for audio-visual ASR

Ist Teil von

• 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002, Vol.1, p.I-853-I-856

Ort / Verlag

IEEE

Erscheinungsjahr

2002

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• 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.