Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

On The Application of Multiple Transition Branch Hidden Markov Models to Chinese Digit Recognition

Xixian Chen, Yinong Li, Xiaoming Ma, Lie Zhang

Beijing University of Posts and Telecommunications, Beijing, P.R.China

In this paper we propose a multiple branch hidden Markov model(MBHMM) which is different from the conventional ones. In the basic HMMs, there is only one transition branch from one state to another one. Our new model has multiple transition branches between two states. As a result, it can hold much more spectral information in the speech signal than the basic HMMs. The evaluation, decoding, and training algorithms associated with MBHMM are also derived. The resulting recognizer is tested on a vocabulary of ten Chinese digits over 20 speakers. The recognition results show that MBHMM significantly outperforms the conventional discrete HMM(DHMM).

Full Paper

Bibliographic reference.  Chen, Xixian / Li, Yinong / Ma, Xiaoming / Zhang, Lie (1994): "On the application of multiple transition branch hidden Markov models to Chinese digit recognition", In ICSLP-1994, 251-254.