標題: Improved methods for characterizing the alternative hypothesis using minimum verification error training for LLR-based 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: speaker recognition;minimization methods;hypothesis testing;minimum verification error
公開日期: 2007
摘要: Speaker verification based on the log-likelihood ratio (LLR) is essentially a task of modeling and testing two hypotheses: the null hypothesis and the alternative hypothesis. Since the alternative hypothesis involves unknown imposters, it is usually hard to characterize a priori. In this paper, we propose a framework to better characterize the alternative hypothesis with the goal of optimally separating client speakers from imposters. The proposed framework is built on either a weighted arithmetic combination or a weighted geometric combination of useful information extracted from a set of pre-trained anti-speaker models. The parameters associated with the combinations are then optimized using Minimum Verification Error training 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.
URI: http://hdl.handle.net/11536/135129
ISSN: 1520-6149
期刊: 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3
起始頁: 65
結束頁: +
Appears in Collections:Conferences Paper