5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Acoustic Modeling based on the MDL Principle for Speech Recognition

Koichi Shinoda, Takao Watanabe

NEC Corporation, Miyamae-ku, Kawasaki, Japan

Recently context-dependent phone units, such as triphones, have been used to model subword units in speech recognition based on Hidden Markov Models (HMMs). While most such methods employ clustering of the HMM parameters(e.g., subword clustering, state clustering, etc.), to control HMM size so as to avoid poor recognition accuracy due to an insuffciency of training data, none of them provide any effective criterion for the optimal degree of clustering that should be performed. This paper proposes a method in which state clustering is accomplished by way of phonetic decision trees and in which the MDL criterion is used to optimize the degree of clustering. Large- vocabulary Japanese recognition experiments show that the models obtained by this method achieved the highest accuracy among the models of various sizes obtained with conventional clustering approaches.

Full Paper

Bibliographic reference.  Shinoda, Koichi / Watanabe, Takao (1997): "Acoustic modeling based on the MDL principle for speech recognition", In EUROSPEECH-1997, 99-102.