文章基本信息

标题：Noise-Robust Speaker Recognition Using Subband Likelihoods and Reliable-Feature Selection
本地全文：下载
作者：Kim, Sung-Tak ; Ji, Mi-Kyong ; Kim, Hoi-Rin 等
期刊名称：ETRI Journal
印刷版ISSN：1225-6463
电子版ISSN：2233-7326
出版年度：2008
卷号：30
期号：1
页码：89-100
语种：English
出版社：Electronics and Telecommunications Research Institute
摘要：We consider the feature recombination technique in a multiband approach to speaker identification and verification. To overcome the ineffectiveness of conventional feature recombination in broadband noisy environments, we propose a new subband feature recombination which uses subband likelihoods and a subband reliable-feature selection technique with an adaptive noise model. In the decision step of speaker recognition, a few very low unreliable feature likelihood scores can cause a speaker recognition system to make an incorrect decision. To overcome this problem, reliable-feature selection adjusts the likelihood scores of an unreliable feature by comparison with those of an adaptive noise model, which is estimated by the maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. To evaluate the effectiveness of the proposed methods in noisy environments, we use the TIMIT database and the NTIMIT database, which is the corresponding telephone version of TIMIT database. The proposed subband feature recombination with subband reliable-feature selection achieves better performance than the conventional feature recombination system with reliable-feature selection.
关键词：Speaker recognition;Gaussian mixture model;universal background model;feature recombination;mel-frequency cepstral coefficient;subband likelihood;reliable feature selection;adaptive noise model