一种小波加权的基音检测方法

A Novel Wavelet-Weighted Pitch Detection Method

噪声环境下的基音检测在语音信号分析和识别中占有重要地位 .自相关法是一种常用的基音检测方法 ,利用自相关法结合小波变换检测信号突变的灵敏性 ,提出了一种噪声环境下有效的基音检测方法 .实验结果表明 ,与传统方法相比 ,该方法鲁棒性好 。

Pitch detection in noisy environment plays an important role in speech analyzing and recognition. Autocorrelation could not precisely detect the pitch though it is the most essential methods in pitch detection. A novel and effective method combining the autocorrelation and wavelet transform was proposed as the wavelet transform is sensitive to sharp the changes of signal. By means of simulation experiments, it is shown that the proposed pitch extraction method is feasible. It behaves more robustly than the conventional methods, and especially effective at low signal to noise ratio.