We present results of an empirical study of the usefulness of different types of features in selecting extractive summaries of news broadcasts for our Broadcast News Summarization System. We evaluate lexical, prosodic, structural and discourse features as predictors of those news segments which should be included in a summary. We show that a summarization system that uses a combination of these feature sets produces the most accurate summaries, and that a combination of acoustic/ prosodic and structural features are enough to build a good' summarizer when speech transcription is not available.
Cite as: Maskey, S., Hirschberg, J. (2005) Comparing lexical, acoustic/prosodic, structural and discourse features for speech summarization. Proc. Interspeech 2005, 621-624, doi: 10.21437/Interspeech.2005-66
@inproceedings{maskey05_interspeech,
author={Sameer Maskey and Julia Hirschberg},
title={{Comparing lexical, acoustic/prosodic, structural and discourse features for speech summarization}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={621--624},
doi={10.21437/Interspeech.2005-66}
}