A speech endpoint detection algorithm based on wavelet transforms

This paper highlights the sub-band average energy variance (SBAEV) approach to perform the endpoint detection process, which involves the segmentation of speech signals from non-speech signals. The SBAEV models have been proposed to perform endpoint detections of isolated digit utterances spoken in the Language. Experiment results obtained from this method are acoustically verified, visually checked and compared to the conventional method of endpoint detection. It was found that the endpoint detection accuracy using the SBAEV approach is very high and encouraging..