Second International Conference on Spoken Language Processing (ICSLP'92)

Banff, Alberta, Canada
October 13-16, 1992

Introducing Neural Predictor to Hidden Markov Model for Speech Recognition

Wei-ying Li, Kechu Yi, Zheng Hu

Lab. 106, Dept. of Info Engineering, Xidian University, Xi'an, China

In this paper, Neural Predictors (NP) are introduced to Hidden Markov Models (HMM) to form a new model HMM / NP for speech recognition. In HMM/NP, each NP is a Multilayer Perceptron (MLP) used as a separate nonlinear predictor, and corresponds to a state in the model. Training and recognition algorithms are given based on Baum-Welch and Back-Propagation (BP) algorithms.Speaker-dependent Mandarin digit recognition experiments were carried out. The performance of forward prediction HMM / NP model and forward-backward prediction HMM / NP model was comparied and a recognition accurcy of 96.2% and 98.7% was obtained respectively. The result indicates that it is effective to use HMM/NP for Mandarin speech recognition.

Full Paper

Bibliographic reference.  Li, Wei-ying / Yi, Kechu / Hu, Zheng (1992): "Introducing neural predictor to hidden Markov model for speech recognition", In ICSLP-1992, 1455-1458.