We study the problem of detecting linguistic events at interword boundaries, such as sentence boundaries and disfluency locations, in speech transcribed by an automatic recognizer. Recovering such events is crucial to facilitate speech understanding and other natural language processing tasks. Our approach is based on a combination of prosodic cues modeled by decision trees, and word-based event N-gram language models. Several model combination approaches are investigated. The techniques are evaluated on conversational speech from the Switchboard corpus. Model combination is shown to give a significant win over individual knowledge sources.
Cite as: Stolcke, A., Shriberg, E., Bates, R., Ostendorf, M., Hakkani, D., Plauche, M., Tur, G., Lu, Y. (1998) Automatic detection of sentence boundaries and disfluencies based on recognized words. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0059, doi: 10.21437/ICSLP.1998-486
@inproceedings{stolcke98_icslp,
author={Andreas Stolcke and Elizabeth Shriberg and Rebecca Bates and Mari Ostendorf and Dilek Hakkani and Madelaine Plauche and Gokhan Tur and Yu Lu},
title={{Automatic detection of sentence boundaries and disfluencies based on recognized words}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0059},
doi={10.21437/ICSLP.1998-486}
}