INTERSPEECH 2008
9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Acoustic Modeling Based on Model Structure Annealing for Speech Recognition

Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Nagoya Institute of Technology, Japan

This paper proposes an HMM training technique using multiple phonetic decision trees and evaluates it in speech recognition. In the use of context dependent models, the decision tree based context clustering is applied to find a parameter tying structure. However, the clustering is usually performed based on statistics of HMM state sequences which are obtained by unreliable models without context clustering. To avoid this problem, we optimize the decision trees and HMM state sequences simultaneously. In the proposed method, this is performed by maximum likelihood (ML) estimation of a newly defined statistical model which includes multiple decision trees as hidden variables. Applying the deterministic annealing expectation maximization (DAEM) algorithm and using multiple decision trees in early stage of model training, state sequences are reliably estimated. In continuous phoneme recognition experiments, the proposed method can improve the recognition performance.

Full Paper

Bibliographic reference.  Shiota, Sayaka / Hashimoto, Kei / Zen, Heiga / Nankaku, Yoshihiko / Lee, Akinobu / Tokuda, Keiichi (2008): "Acoustic modeling based on model structure annealing for speech recognition", In INTERSPEECH-2008, 932-935.