低速率信道环境下鲁棒的说话人确认  

Robust speaker verification in low bit rate channels

作　　者：石如亮[1] 王波[1] 李弼程[1] 高新建[1] 

机构地区：[1]信息工程大学信息工程学院,河南郑州450002

出　　处：《计算机应用》2007年第4期919-921,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60372038)

摘　　要：研究了多种低速率信道环境下,语音编码对与文本无关说话人确认的影响。针对训练和测试语音匹配和不匹配的两种情况下,分别提出了两种方法来提高系统的鲁棒性。在前者中,通过分析语音编码对LPCC参数的影响,提出了一种基于编码失真的LPCC加权参数。在后者中,采用了基于高斯混合模型(GMM)的语音编码检测器,通过判别测试语音的编码类型,选择不同的说话人确认模型。实验结果表明,这两种方法提高了说话人确认系统在多信道条件下的鲁棒性。The influence of speech coding on text-independent speaker verification was studied. Two methods were proposed to improve the robustness of systems under the matched condition and mismatched one, respectively. The weighted LPCC feature based on the distortion of speech coding was explored to reduce the influence under the matched condition. Under the mismatched condition, the solution was to construct multi-models in multi-channels. In this method, a GMM speech coder detector was used to determine the pattern of the testing speech, and then the corresponding speaker verification model was chosen. Experiments show that the two methods can improve the performance of speaker verification in low bit channels.

关 键 词：说话人确认 语音编码 高斯混合模型 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]