| 基于VQ的说话人识别系统的实现 |
| |
| 引用本文： | 王吉林. 基于VQ的说话人识别系统的实现[J]. 高等职业教育, 2004, 13(6): 39-42,48 |
| |
| 作者姓名： | 王吉林 |
| |
| 作者单位： | 盐城工学院电信学院 江苏盐城224003 |
| |
| 摘 要： | 系统以语音信号的LPC倒谱系数、差值倒谱系数、基音周期和差值基音周期的混合特征参数作为识别的特征矢量集,运用矢量量化(VQ)技术实现了与文本有关的说话人识别。在一个10人,1800个语音的语音库上进行了系统的识别实验,其中单音节语音的平均识别率达到了92%,双音节语音达到了96.67%,四音节语音达到了97.67%。系统用于实时识别也收到了较好的效果。
|
| 关 键 词： | 说话人识别 矢量量化 LPC倒谱系数 基音 识别率 |
| 文章编号： | 1008-8415[2004]-06-0039-04 |
| 修稿时间： | 2004-10-20 |
The Realization of the Speaker Recognition System Based on VQ |
| |
| WANG Ji-lin. The Realization of the Speaker Recognition System Based on VQ[J]. Higher Vocational Education:Journal of Tianjin Professional College, 2004, 13(6): 39-42,48 |
| |
| Authors: | WANG Ji-lin |
| |
| Abstract: | This paper is mainly about a text-dependent speaker recognition system based on vector quantification (VQ) methods. We use LPC-derived cepstral coefficients, delta-cepstral coefficients, pitches and delta-pitches as the feature parameter set. Through the test of a speech library composed of 10 speakers and 1800 speeches, we get the fairly high recognition rate, which is about 92% for one-syllable words, about 96.67% for two-syllable words and about 97.67% for four-syllable words. This system can also be used in the real-time speaker recognition. |
| |
| Keywords: | Speaker recognition Vector Quantification LPC-derived cepstral coefficient Pitches Recognition rate |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
