A Novel Algorithm to Robust Speech Endpoint Detection in Noisy Environments

Accurate endpoint detection is crucial for good speech recognition accuracy. A new algorithm based on C0 complexity measure is proposed in this paper. In the comparison of the new algorithm to the other traditional methods such as energy, ZCR, spectral-entropy etc., for the continuous speech and isolated word speech, the C0 complexity feature proved effective. The proposed algorithm is shown to be well suited for the detection of speech endpoint and is very robust for different types of noise, especially for low SNR.