file.pdf (790.04 kB)

Multiple codebook semi-continuous hidden Markov models for speaker-independent continuous speech recognition

Download (790.04 kB)
journal contribution
posted on 01.07.2003 by X. D. Huang, Hsiao-Wuen Hon, Kai-Fu Lee
Abstract: "A semi-continuous hidden Markov model based on multiple vector quantization codebooks is used here for large-vocabulary speaker-independent continuous speech recognition. In the techniques employed here, the semi-continuous output probability density function for each codebook is represented by a combination of the corresponding discrete output probabilities of the hidden Markov model and the continuous Gaussian density functions of each individual codebook. Parameters of the vector quantization codebook and the hidden Markov model are mutually optimized to achieve an optimal model/codebook combination under a unified probabilistic framework. Another advantage of this approach is the enhanced robustness of the semi-continuous output probability density function by the combination of multiple codewords and multiple codebooks. For a 1000-word speaker-independent continuous speech recognition using a word-pair grammar, the recognition error rate of the semi-continuous hidden Markov model was reduced by more than 29% and 40% in comparison to the discrete and continuous mixture hidden Markov model respectively."