基于河南方言的低信噪比下基音检测算法研究

Study of pitch detection algorithm in low SNR based on Henan dialect

基音检测是河南方言语音信号处理中的一个重要环节,针对低信噪比环境下的河南方言语音基音检测准确率低的问题,提出了一种语音信号增强和基音检测相结合的算法。通过多窗谱估计的改进谱减法对语音信号进行降噪处理,对增强后的语音信号用中心削波法消除偏离基音轨迹的野点,再通过自相关法实现基音检测。仿真结果表明,对于低信噪比环境下河南方言语音信号的基音估值检测结果准确,估算出的基音频率和实际基音频率能很好的重合。

Pitch detection is an important part of Henan dialect speech signal processing, for low accuracy issues of Henan dialect pitch detection of noisy speech, the improved pitch detection method was proposed for noisy speech combined with speech enhancement. It reduces speech signal noise by using modified spectral subtraction for multiple window spectral, centre clipping method eliminates outliers deviate from the pitch track for enhanced speech signal, realized pitch detection by ACF. Experimental simulations results show that, the method can detect Henan dialect pitch detection in low SNR, and the estimated pitch frequency coincides with the actual pitch frequency.