噪声环境中基于DTW的说话人识别

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剐系统的识别性能．%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.