多个声源下基于人耳听觉特性的语音分离  

Sound source separation of a multi-voice environment based on human ear listening properties

作　　者：罗元[1] 童开国[1] 张毅[1] 邢武超[1] 陈凯[1] 陈红松[1] 何春江[1] 陈君[1] 

机构地区：[1]重庆邮电大学智能系统及机器人研究所,重庆400065

出　　处：《智能系统学报》2012年第2期121-128,共8页CAAI Transactions on Intelligent Systems

基　　金：科技部国际合作资助项目(2010DF12160);重庆市攻关计划资助项目(CSTC:2010AA2055)

摘　　要：受声学研究启发,结合人脑人耳听觉特性对语音的处理方式,建立了一个完整的模拟听觉中枢系统的语音分离模型.首先利用外周听觉模型对语音信号进行多频谱分析,然后建立重合神经元模型提取语音信号的特征,最后在脑下丘的神经细胞模型中完成对语音的分离.基于现有的语音识别方法,该模型能够很好地解决绝大多数的语音识别方法都只能在单声源和低噪声的环境下使用的问题.实验结果表明,该模型能够实现多声源环境下语音的分离并且具有较高的鲁棒性.随着研究的深入,基于人耳听觉特性的语音分离模型将有很广泛的应用前景.Inspired by acoustics, an integrated voice separation model simulating the central auditory system was established to process a voice by imitating the listening properties of human ears. First, multi-spectral analysis of voice signals was carried out by a peripheral auditory model. Next, a coincidence neuron model was established to extract the features of voice signals. Last, the voices were separated in the cell model of the brain inferior colliculus. Compared to the majority of speech recognition models that can only be used in a single sound source and low- noise environment, this model is a good choice. Experimental results show that the model can separate voices in a multi-sound source environment, thus having a high robustness. With further research, speech separation models based on human ear listening properties will have a wide range of applications.

关 键 词：多声源 人耳听觉特性 双耳时间差 双耳水平差 语音分离 

分 类 号：TN912.3[电子电信—通信与信息系统]