基于感知加权滤波的卡尔曼滤波语音增强

Kalman Filtering Speech Enhancement Based on Perceptual Weighting

结合人耳听觉掩蔽效应,提出一种基于听觉感知加权的卡尔曼滤波语音增强方法。由于人耳对语音的感知主要是通过语音信号频谱分量幅度获得的,引入听觉感知加权滤波器在频域上使共振峰区域残留噪声更多,而共振峰之间及语音幅度谱较低的区域残留噪声减少,这样符合人耳的听觉特性,从而使得主观感觉到的噪声最小。采用语音质量感知评估对语音增强的效果进行评测,与传统的卡尔曼滤波语音增强算法相比,实验结果显示该算法提高了增强语音的质量。

In incorporating masking property of human auditory system, a perceptual weighting based kalman filtering is proposed. The proposed algorithm takes into account the frequency masking properties of the human auditory system and reduces the perceptual effect of the residual noise. Through perceptual weighting filtering, more residual noise signal is redistributed towards formant where it is less audible and less residual noise signal in the valleys of speech spectrum. The redistribution could make the residual noise perceptually inaudible. The quality of the enhanced speech is evaluated by perceptual evaluation of speech quality （PESQ） scores. Experimental results show that the proposed algorithm achieves certain improvement on output speech quality as compared to conventional KF algorithm.