一种基于人耳掩蔽效应和无语音概率的谱减语音增强算法

提出一种基于听觉掩蔽模型和无语音概率的语音增强算法。该算法对听觉掩蔽模型进行了适当的修正,通过引入无语音概率(SAP)思想动态地确定每一帧语音信号各个关键频率段的听觉掩蔽阈值,有选择性地进行谱减。仿真结果表明所提出的算法优于一般掩蔽增强算法,能够有效地减少音乐噪声并且更符合人耳听觉特性,特别是在低信噪比的情况下,语音具有更好的清晰度和可懂度。

A Speech Enhancement Algorithm Based on Masking Property of Human Auditory System and Speech Absence Probability

An approach to speech enhancement based on masking properties of human auditory system and Speech Absent Probability(SAP) is presented.In this approach,the masking model of human auditory is modified,the masking thresholds of the key frequency segments of each speech frame are determined dynamically through introducing the speech absence probability.Experimental results demonstrate that the proposed algorithm has better performance of speech articulation and reduces the musical noise compared to another modified spectral subtraction algorithms under the same level of noise reduction,and this superiority is more significant at very low SNR.