Using prosodic information to constrain language models for spoken dialogue

Author

Taylor, Paul ; Shimodaira, Hiroshi ; Isard, Stephen ; King, Simon ; Kowtko, Jaqueline

Author_Institution

Centre for Speech Technol. Res., Edinburgh Univ., UK

Volume

1

fYear

1996

fDate

3-6 Oct 1996

Firstpage

216

Abstract

We present work intended to improve speech recognition performance for computer dialogue by taking into account the way that dialogue context and intonational tune interact to limit the possibilities for what an utterance might be. We report on the extra constraint achieved in a bigram language model, expressed in terms of entropy, by using separate submodels for different sorts of dialogue acts, and trying to predict which submodel to apply by analysis of the intonation of the sentence being recognised

Keywords

human factors; interactive systems; natural language interfaces; speech recognition; bigram language model; computer dialogue; dialogue acts; dialogue context; entropy; intonational tune; prosodic information; sentence recognition; speech recognition performance; spoken dialogue; Bridges; Entropy; Game theory; Natural languages; Neural networks; Performance analysis; Power system modeling; Predictive models; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607080

Filename

607080