噪声环境中基于DTW的说话人识别  

Analysis of DTW to Speaker Recognition in Noisy Environment

作　　者：张飞云[1] 张鹏 高建生 

机构地区：[1]许昌学院电气信息工程学院,河南许昌461000 [2]南召电业局,河南南召474650 [3]许昌电视台,河南许昌461000

出　　处：《许昌学院学报》2011年第5期68-72,共5页Journal of Xuchang University

基　　金：河南省教育厅自然科学研究资助计划项目(2009A510011)

摘　　要：在VC++环境下,提取PLAR特征参数,基于听觉特性和语谱特性的语音增强器作为预处理器,对语音信号首先进行降噪处理,建立了基于DTW的抗噪声说话人识别系统.实验结果表明,即使在信噪比比较低的情况下,该系统都会在一定程度上提高多种噪声环境下说话人识别系统的识别性能.Anti-noise speaker recognition system is established based on extracting PLAR as the voice feature parameters, and the DTW as the model matching method. Speech enhancement method based on the auditory characteristics and the speech spectrum characteristics is used to reduce the noise. Experimental results show that the performance of speaker identification system can be improved to some extent in different noisy environments even when the signal noise ratio is low.

关 键 词：说话人识别 动态时间弯折(DTW) PLAR 听觉特性 语谱特性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]