基于Mel频率倒谱参数相似度的语音端点检测算法

Voice activity detection algorithm based on Mel frequency cepstrum coefficient(MFCC) similarity

为提高噪声环境下语音端点检测的精确性,提出了一种基于Mel频率倒谱参数(MF-CC)相似度的端点检测方法。提取了每帧语音信号的Mel频率倒谱参数,然后将前十帧作为背景噪声,计算测试帧和背景噪声的MFCC相关系数距离,最后用得到的MFCC相似度距离曲线进行端点检测。实验结果表明,该方法在白噪声和粉噪声环境下均可得到理想的端点检测效果,并且在低信噪比时仍然有效。

To improve the accuracy of Voice Activity Detection（VAD） under noisy Environment,a voice activity detection algorithm based on Mel Frequency Cepstrum Coefficient（MFCC） similarity is proposed.First,the MFCC from each frame of the voice signals is extracted.Then,the first ten frames are taken as the background noises.Finally,by calculating the MFCC correlation coefficient distance under the above noisy condition,the voice-activity parameters are detected from the MFCC similarity curves.The experiment results show that the proposed algorithm is effective under both white noise and pink noise conditions and at low signal to noise ratio.