標題: Improving the characterization of the alternative hypothesis via minimum verification error training with applications to speaker verification
作者: Chao, Yi-Hsiang
Tsai, Wei-Ho
Wang, Hsin-Min
Chang, Ruei-Chuan
資訊工程學系
Department of Computer Science
關鍵字: Genetic algorithm;Hypothesis testing;Log-likelihood ratio;Minimum verification error training;Speaker verification
公開日期: 1-七月-2009
摘要: Speaker verification is usually formulated as a statistical hypothesis testing problem and solved by a log-likelihood ratio (LLR) test. A speaker verification system's performance is highly dependent on modeling the target speaker's voice (the null hypothesis) and characterizing non-target speakers' voices (the alternative hypothesis). However, since the alternative hypothesis involves unknown impostors, it is usually difficult to characterize a priori. in this paper, we propose a framework to better characterize the alternative hypothesis with the goal of optimally distinguishing the target speaker from impostors. The proposed framework is built on a weighted arithmetic combination (WAC) or a weighted geometric combination (WGC) of useful information extracted from a set of pre-trained background models. The parameters associated with WAC or WGC are then optimized using two discriminative training methods, namely, the minimum verification error (MVE) training method and the proposed evolutionary, MVE (EMVE) training method, such that both the false acceptance probability and the false rejection probability are minimized. Our experiment results show that the proposed framework Outperforms conventional LLR-based approaches. (C) 2008 Elsevier Ltd. All rights reserved.
URI: http://dx.doi.org/10.1016/j.patcog.2008.10.015
http://hdl.handle.net/11536/7017
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2008.10.015
期刊: PATTERN RECOGNITION
Volume: 42
Issue: 7
起始頁: 1351
結束頁: 1360
顯示於類別:期刊論文


文件中的檔案:

  1. 000265365500014.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。