论文信息 - Improvements in HMM-based isolated word recognition system

Improvements in HMM-based isolated word recognition system

A speaker independent isolated word recognition system for voice activated robots is introduced. Since such an application requires a fast and accurate recognition system, discrete hidden Markov models and vector quantisation techniques have been used. Different initialisations for VQ and HMM training are tested to obtain improvements over the other systems. The final models can be evaluated using a temporal normalisation of the HMM scores. A threshold based rejector can also be established using this temporal normalisation.

Antonio M. Peinado | Victoria E. Sánchez | José C. Segura | J. M. Lopez | A. J. Rubio Ayuso

[1] L. Rabiner,et al. An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[2] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[3] J. Makhoul,et al. Vector quantization in speech coding , 1985, Proceedings of the IEEE.

[4] Lawrence R. Rabiner,et al. An algorithm for determining the endpoints of isolated utterances , 1975, Bell Syst. Tech. J..

[5] R. Gray,et al. Speech coding based upon vector quantization , 1980, ICASSP.

[6] Julius T. Tou,et al. Pattern Recognition Principles , 1974 .

[7] John E. Markel,et al. Linear Prediction of Speech , 1976, Communication and Cybernetics.

[8] Ronald W. Schafer,et al. Digital Processing of Speech Signals , 1978 .

[9] L. R. Rabiner,et al. An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[10] J. Makhoul,et al. Linear prediction: A tutorial review , 1975, Proceedings of the IEEE.