Abstract:
This paper presents a multiple templets matching algorithm based on feature space trace, which is used in speaker recognition. Experiments show this method is a robust, high recognizable and valuable way to implement text-dependent speaker recognition. ;;
摘要： 提出一种用于说话人识别的方法基于特征空间轨迹的多模板匹配法。实验结果表明,该方法具有识别率高稳健性强确认可靠,是--, , 一种实现与文本相关的说话人识别的实用方法。
关键词:
说话人识别,
特征空间轨迹规整化,
模糊聚类
CLC Number:
HUANG Nanhua, WU Yadong, LI Zhizhu. Speaker Recognizing System Based on Feature Space Trace Multiple Templets Matching[J]. , 2001, 27(05): 126-128.
黄南华,吴亚栋,李治柱. 基于特征空间轨迹多模板匹配的说话人识别研究[J]. , 2001, 27(05): 126-128.