The 2012 Nist Speaker Recognition Evaluation

14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5(2013)

引用 69|浏览105
暂无评分
摘要
In 2012 NIST held the latest in an ongoing series of text independent speaker recognition evaluations (SRE's). The 2012 NIST Speaker Recognition Evaluation (SRE12) was the largest and most complex SRE to date, including over 100 million trials. Several aspects of SRE12 were new; most significantly, NIST released in advance of the evaluation target speaker training data from six preexisting corpora, and systems were permitted to utilize joint information from target speakers for speaker modeling and test segment scoring. Results from the evaluation suggest that systems found it easier to reject non-target trials where the test speaker was among the target speakers.
更多
查看译文
关键词
speaker recognition,speaker detection,NIST SREs,standard reference data
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要