摘要
采用线性预测倒谱系数(linear prediction cepstrum coefficient,LPCC)作为语音的特征参数,矢量量化(vector quantity,VQ)方法进行模式匹配,探讨声纹识别以实现身份认证,并对此识别方法进行了相关的实验.通过验证,这种方法可以区分不同的说话人,并且在做说话人辨认实验时可达到较高的识别率.
Taking LPCC as the voice feature parameters, the VQ as the model matching method,the correlative experiment is carried on. Experimental result proves that this method can distinguish different speakers, and has a high precision of recognition to speaker identification.
出处
《西安工程科技学院学报》
2007年第6期848-851,共4页
Journal of Xi an University of Engineering Science and Technology
