基于语音谐波结构的鲁棒特征参数及其在说话人识别中的应用  

Robust Feature Based on Speech Harmonic Structure for Speaker Identification

作　　者：张玲华[1] 郑宝玉[1] 杨震[1] 

机构地区：[1]南京邮电大学通信与信息工程学院,南京210003

出　　处：《电子与信息学报》2006年第10期1786-1789,共4页Journal of Electronics & Information Technology

基　　金：江苏省"青蓝工程"跨世纪学术带头人专项基金(QL003YZ);南京邮电大学科研发展基金(2001院17)资助课题

摘　　要：通过对纯净语音及含噪语音短时谱的分析比较,提出了一种基于基音频率及其谐波结构的新的语音特征参数。实验表明,与传统的倒谱特征相比,新特征对加性白噪声相对较不敏感,在闭集文本无关说话人识别中,新特征可以在加性白高斯噪声环境下提高系统的说话人识别率。An effective and robust speech feature extraction method based on pitch frequency and harmonic structure is proposed by means of short-time spectrum analysis of clear and noisy speech. Experimental results indicate that the new feature is relatively insensitive to Additive White Gaussian Noise （AWGN）. Compared to conventional cepstrums, the new feature can give outstanding improvement for closed-set text-independent speaker identification under noisy environments corrupted by AWGN.

关 键 词：说话人识别 短时谱 谐波特征 基音频率 

分 类 号：TN912.3[电子电信—通信与信息系统]