Punctuation Annotation using Statistical Prosody Models

Heidi Christensen, Yoshihiko Gotoh, Steve Renals

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationProceedings of the ITRW on Prosody in Speech Recognition and Understanding
Subtitle of host publicationProsody 2001
Number of pages6
Publication statusPublished - 2001
EventITRW on Prosody in Speech Recognition and Understanding (Prosody 2001) - Molly Pitcher Inn, Red Bank, NJ, United States
Duration: 22 Oct 200124 Oct 2001


WorkshopITRW on Prosody in Speech Recognition and Understanding (Prosody 2001)
Country/TerritoryUnited States
CityRed Bank, NJ


Dive into the research topics of 'Punctuation Annotation using Statistical Prosody Models'. Together they form a unique fingerprint.

Cite this