Prosody in Speech Recognition and Understanding October 22-24, 2001 Molly Pitcher Inn, Red Bank, NJ, USA

Punctuation Annotation using Statistical Prosody Models

Heidi Christensen, Yoshihiko Gotoh, Steve Renals

University of Sheffield, Department of Computer Science. Sheffield, UK

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.

Full Paper (PDF)   Full Paper (Zipped Postscript)

Bibliographic reference.  Christensen, Heidi / Gotoh, Yoshihiko / Renals, Steve (2001): "Punctuation annotation using statistical prosody models", In Prosody-2001, paper 6.