关键词: 自适应, 语音端点检测, Mel能量, 时频参数

Abstract: In order to solve the inferior performance and sad self-adaptive of the traditional voice activity detection algorithm in an environment with low Signal to Noise Ratio （SNR）, a new self-adaptive voice activity detection algorithm based on TF parameters is put forward. After introducing the time-domain log-energy and improved mel-scale energy, the new Time-Frequency （TF） parameters are acquired by coalescing them, which make it possible for distinguishing speech from noise effectively. Then, the TF parameters are updated to predicate endpoint through the threshold test. Simulation experiments show that the algorithm has better robustness and more precise detection. When the SNR is 0 dB, the error rate of the algorithm is about 15%.

Key words: self-adaptive, voice activity detection, Mel-scale log-energy, Time-Frequency（TF） parameter