MODELING THE PROSODY OF HIDDEN EVENTS FOR IMPROVED WORD RECOGNITION

Andreas Stolcke, Elizabeth Shriberg, Dilek Hakkani-Tür, Gökhan Tür

Research output: Contribution to conferencePaperpeer-review

Abstract

We investigate a new approach for using speech prosody as a knowledge source for speech recognition. The idea is to penalize word hypotheses that are inconsistent with prosodic features such as duration and pitch. To model the interaction between words and prosody we modify the language model to represent hidden events such as sentence boundaries and various forms of disfluency, and combine with it decision trees that predict such events from prosodic features. N-best rescoring experiments on the Switchboard corpus show a small but consistent reduction of word error as a result of this modeling. We conclude with a preliminary analysis of the types of errors that are corrected by the prosodically informed model.

Original languageEnglish (US)
Pages311-314
Number of pages4
StatePublished - 1999
Externally publishedYes
Event6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 - Budapest, Hungary
Duration: Sep 5 1999Sep 9 1999

Conference

Conference6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Country/TerritoryHungary
CityBudapest
Period9/5/999/9/99

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Linguistics and Language
  • Communication

Fingerprint

Dive into the research topics of 'MODELING THE PROSODY OF HIDDEN EVENTS FOR IMPROVED WORD RECOGNITION'. Together they form a unique fingerprint.

Cite this