A Chinese phoneme clustering theory and its application to a text independent speaker verification system

This paper presents a new idea of Chinese phoneme clustering and a text independent speaker verification system with this technique applied. It changes the way of conventional verification method with averaging features used, instead, both the dynamic and static features of speech are included in our new method. Also it leads to fast and efficient clustering algorithm in the training phase. The final decision is made upon the statistical probability criterion.Finally, A practical speaker verification system based on the Chinese phoneme clustering theory has been realized by using the TMS32010 microprocessor. The recognition accuracies are 99% (for text dependent) and 95% (for text independent).