An adaptive speech endpoint detection method in low SNR environments

Endpoint detection of speech has been shown prosperous for speech recognition and speech enhancement. But the traditional endpoint detection methods lose efficiency in either low signal-to-noise ratio (SNR) environments or nonstationary noise environments. To improve the accuracy of speech endpoint detection in low SNR environments, an endpoint detection method based on an adaptive algorithm for thresholds adjustment is put forward in this paper. The spectral subtraction of multitaper spectrum estimation is performed to enhance the speech. During the process of detection, the cepstral distance of Mel frequency cepstrum coefficient (MFCC) is utilized and the thresholds are adaptively adjusted to different environments. Simulation experiments indicate that in different noise environments with different SNRs, our algorithm has a better endpoint detection accuracy compared with other detection algorithms. Besides that, the algorithm also exhibits strong robustness in low SNR environments.