计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (15): 148-151.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于韵律特征的SVM说话人确认

黄肖忠,李 辉,许东星,郭 伟   

  1. 中国科学技术大学 电子科学与技术系,合肥 230027
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-05-21 发布日期:2011-05-21

SVM speaker verification based on prosodic feature

HUANG Xiaozhong,LI Hui,XU Dongxing,GUO Wei   

  1. Department of Electronic Science and Technology,University of Science and Technology of China,Hefei 230027,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-21 Published:2011-05-21

摘要: 提出了一种基于韵律特征和SVM的文本无关说话人确认系统。采用小波分析方法,从语音信号的MFCC、F0和能量轨迹中提取出超音段韵律特征,通过实验研究三者的韵律特征在特征层的最佳互补融合,得到信号的韵律特征PMFCCFE,用韵律特征的GMM均值超矢量作为参数训练目标话者的SVM模型,以更有效地区分目标话者和冒认话者。在NIST06 8side-1side数据库的实验表明,以短时倒谱参数的GMM-UBM系统为基准,超音段韵律特征的GMM-SVM系统的EER相对下降了57.9%,MinDCF相对下降了41.4%。

关键词: 韵律特征, 高斯混合模型(GMM)超矢量, 支持向量机, 文本无关说话人确认

Abstract: A text-independent speaker verification method based on prosodic features and SVM model is proposed.With wavelet analysis,prosodic features are extracted from MFCC,F0 and energy contours respectively,these complementary features are fused at feature level to yield a most effective feature PMFCCFE,GMM mean supervectors of PMFCCFE are used to train SVM models to discriminates target speakers and imposters more effectively.The experiments conducted on the 2006 NIST 8side-1side subset show that the prosodic GMM-SVM system relatively improves the performance of the verification system by 57.9% in EER,41.4% in MinDCF,compared with the MFCC-based GMM-UBM system.

Key words: prosodic features, Gaussian Mixture Model(GMM) supervector, Support Vector Machine(SVM), text-independent speaker verification