Sixth International Conference on Spoken Language Processing

A semicontinuous segmental probability model, which can be considered as a special form of continuous mixture segmental probability model with continuous output probability density functions sharing in a mixture Gaussian density codebook, is proposed in this paper. The amount of training data required, as well as the computational complexity of the semicontinuous segmental probability model(SCSPM)[2], can be significantly reduced in comparison with the continuous segmental probability model(CSPM). Parameters of the vector quantization codebook and segmental probability model can be mutually optimized to achieve an optimal model/codebook combination, which leads to a unified modeling approach to vector quantization and segmental probability modeling of speech signals. The experimental results show that the recognition accuracy of the semicontinuous segmental probability model is higher than the semicontinuous hidden Markov model and continuous segmental probability model.
Keywords: hidden Markov model, segmental probability model, semicontinuous segmental probability model, speech recognition
Bibliographic reference. Liu, Jun / Zhu, Xiaoyan / Jia, Bin (2000): "Semicontinuous segmental probability model for speech signals", In ICSLP2000, vol.4, 640643.