Abstract: In order to improve the adaptability and robustness of speech endpoint detection, this paper presented a algo- rithm for speech endpoint detection based on wavelet analysis and support vector machine. Firstly, the characteristic quantities of speech signals are obtained by the wavelet transformation. Then the input to support vector machine can be computed based on these characteristic quantities. Finally the signal's type can be determined. The simulation experi- menu results show that the proposed algorithm improves the detection rate, has better adaptability and robustness, and can detect signals with different SNR, compared with the traditional detection algorithms.

Key words: Wavelet analysis, Support vector machine, Speech Endpoints, Feature extraction