A voice activity detection algorithm with sub-band detection based on time-frequency characteristics of mandarin

Voice activity detection algorithms are widely used in the areas of voice compression, speech synthesis, speech recognition, speech enhancement, and etc. In this paper, an efficient voice activity detection algorithm with sub-band detection based on time-frequency characteristics of mandarin is proposed. The proposed sub-band detection consists of two parts: crosswise detection and lengthwise detection. Energy detection and pitch detection are in the range of considerations. For a better performance, double-threshold criterion is used to reduce the misjudgment rate of the detection. Performance evaluation is based on six noise environments with different SNRs. Experiment results indicate that the proposed algorithm can detect the area of voice effectively in non-stationary environment and low SNR environment and has the potential to progress.