基于因子分析和特征映射的耳语说话人识别  

Whispered Speaker Identification Based on Factor Analysis and Feature Mapping

作　　者：张庆芳[1] 赵鹤鸣[1] 龚呈卉[1] 

机构地区：[1]苏州大学电子信息学院,苏州215006

出　　处：《数据采集与处理》2016年第2期362-369,共8页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61071215;61372146)资助项目;苏州市科技计划(SYG201033)资助项目

摘　　要：为了解决耳语音识别系统中训练语音和测试耳语音来自不同发音模式的失配问题,本文提出一种基于联合因子分析(Joint factor analysis,JFA)与特征映射(Feature mapping,FM)的失配信息补偿算法。该算法首先用联合因子分析法计算说话人发音模式信息,并对发音模式因子和发音模式空间参数进行优化,接着对语音参数用发音模式信息进行特征映射后再进行训练和识别,以减少发音模式对系统的影响。实验结果表明,基于因子分析和特征映射的方法可以有效地提取训练语音中的说话人信息,提高耳语识别系统的识别率。Aiming at the mismatch between training speech and test speech from different speaking man‐ners ,a kind of feature processing algorithm is proposed based on joint factor analysis and feature map‐ping .The speaking mode information is extracted by joint factor analysis algorithm ,then the speaking mode factor and space are optimized .Before training and test ,the feature is mapped by speaking mode in‐formation to reduce the speaking mode effects .The experimental results show that the proposed algo‐rithm can effectively extract the speaker information of the training speech ,and improve the recognition rate of w hispered speaker recognition system .

关 键 词：耳语说话人识别 联合因子分析 特征映射 正常音 耳语音 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]