通过分离语音空间和说话人空间的说话人识别  

Speaker recognition based on separating speech space and speaker space

作　　者：邱政权[1] 尹俊勋[2] 

机构地区：[1]湖南科技大学信息与电气工程学院,湖南湘潭411201 [2]华南理工大学电信学院,广州510640

出　　处：《计算机工程与应用》2008年第12期212-214,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60275005);广东省自然科学基金重点项目(the Natural Science Foundation of Guangdong Province of China under Grant No.04105938)

摘　　要：在说话人空间中,存在语音特征随句子和时间差异而变化的问题。这个变化主要是由语音数据中的语音信息和说话人信息的变化引起的。如果把这两种信息彼此分离就能实现鲁棒的说话人识别。在假设大的说话人变量的空间为"语音空间"和小的说话人变量的空间为"说话人空间"的情况下,通过子空间方法分离语音信息和说话人信息,提出了说话人辨认和说话人确认方法。结果显示:通过相对于传统方法的比较试验,能用小量训练数据建立鲁棒说话人模型。In speaker space,it occurs that speech varies with the difference of the sentence and time.This variability is mainly aroused with the variable speech information and speaker information in the speech database.If these two kinds of information are separated,robust speaker recognition is done.In this paper,on the assumption that large speaker variable space is ＂speech space＂ and small speaker variable space is ＂speaker space＂,speaker identification and speaker verification are presented by separating speech information and speaker information with subspace method.The result shows small quantity train databases can be used to set up robust speaker model by comparative experiments compared to traditional method.

关 键 词：说话人识别 语音空间 说话人空间 线性判决分析(LDA) 

分 类 号：TN912.34[电子电信—通信与信息系统]