Prosody-dependent acoustic modeling using variable-parameter hidden markov models

Jui Ting Huang, Po Sen Huang, Yoonsook Mo, Mark Hasegawa-Johnson, Jennifer Cole

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

1 Scopus citations

Abstract

As an effort to make prosody useful in spontaneous speech recognition, we adopt a quasi-continuous prosodic annotation and accordingly design a prosody-dependent acoustic model to improve ASR performances. We propose a variable-parameter Hidden Markov Models, modeling the mean vector as a function of the prosody variable through a polynomial regression model. The prosodically-adapted acoustic models are used to re-score the N-best output from a standard ASR, according to the prosody variable assigned by an automatic prosody detector. Experiments on the Buckeye corpus demonstrate the effectiveness of our approach.

Original languageEnglish (US)
Title of host publication5th International Conference on Speech Prosody 2010
PublisherInternational Speech Communications Association
ISBN (Electronic)9780000000002
StatePublished - 2010
Externally publishedYes
Event5th International Conference on Speech Prosody: Every Language, Every Style, SP 2010 - Chicago, United States
Duration: May 10 2010May 14 2010

Publication series

NameProceedings of the International Conference on Speech Prosody
ISSN (Print)2333-2042

Conference

Conference5th International Conference on Speech Prosody: Every Language, Every Style, SP 2010
Country/TerritoryUnited States
CityChicago
Period5/10/105/14/10

Keywords

  • Prosody-dependent ASR
  • Re-scoring
  • Variable parameter HMM

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Prosody-dependent acoustic modeling using variable-parameter hidden markov models'. Together they form a unique fingerprint.

Cite this