摘要
为提高低信噪比环境下语音端点检测算法性能不高的问题,提出将MFCC倒谱距离与对数能量结合进行端点检测。首先,对语音计算对数能量,然后计算改进的倒谱距离,将MFCC倒谱距离与对数能量融合,获得了一种新的语音参数,该参数能有效地提高低信噪比情况下语音与噪声的区别,对参数进行顺利滤波用于语音端点检测,采用自动更新的双阈值进行语音端判别。仿真实验表明,该算法具有较好的适用不同噪声,在低信噪比下依然能获得比较理想的端点检测效果。
In order to solve the inferior performance of the voice activity detection algorithm in an environment with low signal to Noise Ratio （SNR） , a new voice activity detection algorithm based on the the mel frequency cepstrum coefficients （MFCC） distance and the logarithmic energy is put forward.Firsly, The proposed scheme is to calculate the logarithmic energy of speech, then calculate the MFCC distance, one new speech parameter is obtained by fusing the MFCC distance and the logarithmic energy. Then, the parameter distinguishs speech from noise effectively in an envil＇onment with low signal to noise ratio after with an order statistics filter .Simulation experiments show that the algorithm has more precise detection with different noise.In low SNR the algorithm can still get the ideal endpoint detection results.
出处
《电声技术》
2016年第9期51-55,共5页
Audio Engineering
基金
国家自然科学基金项目(51304247)
湖南教育厅科研项目(14C0759)
