基于子带ICA-R和收缩函数后处理的语音增强方法

A Speech Enhancement Method Based on ICA-R in Subband and Shrinkage Function Post-Processing

针对噪声和混响情况下的语音增强问题,本文给出一种基于子带独立分量分析(ICA-R)算法和收缩函数后处理的语音增强方法.该方法将ICA-R和收缩函数算法相结合,在噪声和混响环境中通过对两路带噪语音信号进行增强处理,以实现增强目标语音信号的目的.首先对两路带噪语音信号进行子带分解;然后在子带内利用ICA-R算法从带噪语音信号中提取出子带目标信号,再经过综合滤波器形成全带目标信号;最后,将该信号经收缩函数后处理,得到增强后的目标语音信号.用实际录制的带噪语音信号对本文方法进行了测试,实验结果表明,该方法具有较强的噪声抑制能力,对语音信号造成的损伤较小.

A speech enhancement method based on independent component analysis with reference （ICA- R） in subband and shrinkage function post-processing is proposed, which is used in noise and reverberation en- vironments. Combining ICA-R and shrinkage function, two channel noisy signals were processed to obtain the enhanced target signal. Firstly, two channel noisy signals were passed through the analysis filter banks to gener- ate the subband noisy signals. Then, ICA-R was used in subband to extract the estimated target signal we were interested in. Finally, after synthesis filter banks, shrinkage function was used to enhance estimated target signal further. Experiments were performed using noisy speech signals recorded in practical environment and simulated in incoherent, diffused and coherent noise field separately. The experimental results show that the proposed method is effective and the distortion of the target signal is small.