机构地区: 东南大学信息科学与工程学院无线电工程系
出 处: 《电声技术》 2003年第10期11-14,共4页
摘 要: 文中以语音信号的LPC倒谱系数、Δ倒谱系数、基音周期和Δ基音周期的混合特征参数作为识别说话人的特征,运用VQ技术实现了说话人自动识别。在10个说话人,1800个汉语数字和单词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%。 This paper presents the realization of a text-dependent speaker recognition system based on VQ methods by using LPC-derived cepstral coefficients,delta-cepstral coefficients,pitches and delta-pitches as the feature parameter set.Through the test of a speech library composed of10speakers and1800speeches of Chi nese numbers and words,fairly high recognition rates,which is about 92%for one-syllable words,96.67%for two-syllable words and97.67%for four-syllable words are reached.