This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub-4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task.
Cite as: Christensen, H., Gotoh, Y., Renals, S. (2001) Punctuation annotation using statistical prosody models. Proc. ITRW on Prosody in Speech Recognition and Understanding, paper 6
@inproceedings{christensen01_prosody,
author={Heidi Christensen and Yoshihiko Gotoh and Steve Renals},
title={{Punctuation annotation using statistical prosody models}},
year=2001,
booktitle={Proc. ITRW on Prosody in Speech Recognition and Understanding},
pages={paper 6}
}