Improved methods for characterizing the alternative hypothesis using minimum verification error training for LLR-based speaker verification
檔案
本條目沒有附加檔案。
日期
2007
類型
系所
期刊名稱
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3
卷期與頁次
頁 65–+
ISSN
1520-6149
語言
英文
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.
所屬典藏
會議論文引用此條目
Chao, Y.-H., Tsai, W.-H., Wang, H.-M., & Chang, R.-C. (2007). Improved methods for characterizing the alternative hypothesis using minimum verification error training for LLR-based speaker verification. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 65–+. https://ir.lib.nycu.edu.tw/handle/11536/135129
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/135129