Reranking for Sentence Boundary Detection in Conversational Speech

Brian Roark,Yang Liu,Mary P. Harper,Robin Stewart,Matthew Lease,Matthew G. Snover,Izhak Shafran,Bonnie J. Dorr,John Hale,Anna Krasnyanskaya,Lisa Yung

2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13（2006）

引用 62|浏览96

暂无评分

摘要

We present a reranking approach to sentence-like unit (SU) boundary detection, one of the EARS metadata extraction tasks. Techniques for generating relatively small n-best lists with high oracle accuracy are presented. For each candidate, features are derived from a range of information sources, including the output of a number of parsers. Our approach yields significant improvements over the best performing system from the NIST RT-04F community evaluation

查看译文

关键词

meta data,speech recognition,EARS metadata extraction tasks,NIST RT-04F community evaluation,conversational speech,oracle accuracy,reranking,sentence-like unit boundary detection

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