改进VQ算法在说话人识别中的应用

Text-independent Speaker Recognition Based on Improved VQ Algorithm

与文本无关的说话人识别方法是当前说话人识别技术的研究重点。基于矢量量化的说话人识别,因其运算过程简单等特点,在说话人识别领域有着广泛的应用。本文对矢量量化的码书形成算法进行了改进,并基于改进算法进行了与文本无关的说话人识别。经实验结果证明,本文的方法改善了码本的性能,提高了说话人识别的识别率。

The text-independent speaker recognition is an important part of speaker recognition. Vector quantization （VQ）, without regard to the difficult speech segment and the complex time warping, becomes a useful method for text-independent speaker recognition. This paper proposes a method to improve the algorithm of forming codebooks, and apply it to text-independent speaker recognition. The simulation shows the method improved the quality of the codebook, and increases the right rate.