10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Deterministic Annealing Based Training Algorithm for Bayesian Speech Recognition

Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda

Nagoya Institute of Technology, Japan

This paper proposes a deterministic annealing based training algorithm for Bayesian speech recognition. The Bayesian method is a statistical technique for estimating reliable predictive distributions by marginalizing model parameters. However, the local maxima problem in the Bayesian method is more serious than in the ML-based approach, because the Bayesian method treats not only state sequences but also model parameters as latent variables. The deterministic annealing EM (DAEM) algorithm has been proposed to improve the local maxima problem in the EM algorithm, and its effectiveness has been reported in HMM-based speech recognition using ML criterion. In this paper, the DAEM algorithm is applied to Bayesian speech recognition to relax the local maxima problem. Speech recognition experiments show that the proposed method achieved a higher performance than the conventional methods.

Full Paper

Bibliographic reference.  Shiota, Sayaka / Hashimoto, Kei / Nankaku, Yoshihiko / Tokuda, Keiichi (2009): "Deterministic annealing based training algorithm for Bayesian speech recognition", In INTERSPEECH-2009, 680-683.