HARMONIC STRUCTURE FEATURES FOR ROBUST SPEAKER RECOGNITION AGAINST CHANNEL EFFECT

摘要：

This paper proposes a novel feature set for robust speaker recognition, which is based on the harmonic structure of speech signals. Channel modulation effects are supposed to be weakened in the harmonic structure features, and furthermore the influence introduced by channel variability could be diminished to a certain degree. Though experiment results show that the raw performance of the harmonic structure features is not better than our baseline system due to some inevitable information lost, significant improvement of average 9.85% relative minCost decrease has been made by a score fusion approach with baseline features.

关键词： Speaker recognition channel effect reduction harmonic structure sinusoidal resynthesis score fusion

作者: Chuan Cao Xiang Xiao Ming Li Man Liu Yonghong Yan

作者单位: ThinkIT Speech Lab., Institute of Acoustics, Chinese Academy of Sciences, Beijing ThinkIT Speech Lab., Institute of Acoustics,Chinese Academy of Sciences, Beijing ThinkIT Speech Lab.,Institute of Acoustics, Chinese Academy of Sciences, Beijing

会议类型: 国际会议

会议名称: Second International Symposium on Information Science and Engineering(第二届信息科学与工程国际会议)

会议地点: 上海

会议语种:英文

页码: 451-454

在线出版日期: 2009-12-26（万方平台首次上网日期，不代表论文的发表时间）