TY - CONF T1 - Reranking for Sentence Boundary Detection in Conversational Speech T2 - 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings Y1 - 2006 A1 - Roark,B. A1 - Liu,Yang A1 - Harper,M. A1 - Stewart,R. A1 - Lease,M. A1 - Snover,M. A1 - Shafran,I. A1 - Dorr, Bonnie J A1 - Hale,J. A1 - Krasnyanskaya,A. A1 - Yung,L. KW - Automatic speech recognition KW - conversational speech KW - data mining KW - Ear KW - EARS metadata extraction tasks KW - Feature extraction KW - hidden Markov models KW - meta data KW - Model driven engineering KW - NIST KW - NIST RT-04F community evaluation KW - oracle accuracy KW - performance evaluation KW - reranking KW - sentence-like unit boundary detection KW - Speech processing KW - Speech recognition KW - Telephony AB - 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 JA - 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings PB - IEEE VL - 1 SN - 1-4244-0469-X M3 - 10.1109/ICASSP.2006.1660078 ER -