Improved speech endpoint detection algorithm in strong noise environment
LU Yuanya · Journal of Computer Applications · 2014
To improve the correctness of speech endpoint detection in strong noise environment,and overcome the disadvantage in traditional dual-threshold speech endpoint detection based on short-time energy and short-time zero-crossing rate,whose performance degrades sharply in low Signal-to-Noise Ratio(SNR) environment,an improved speech endpoint detection algorithm was proposed.In this method,the noisy speech signal was de-noised to enhance SNR at first,then the dual-threshold speech endpoint detection algorithm was used to detect the endpoints of the de-noised speech signal.The experimental results indicate that the proposed method not only has strong robustness,but also can achieve high detection accuracy in strong noise environment,so the effectiveness of the algorithm is proved.