Using Prosodic Information to Constrain Language Models for Spoken dialogue

Paul Taylor; Hiroshi Shimodaira; Stephen Isard; Simon King; Jacqueline Kowtko

doi:10.1109/ICSLP.1996.607080

Using Prosodic Information to Constrain Language Models for Spoken dialogue

Paul Taylor, Hiroshi Shimodaira, Stephen Isard, Simon King, Jacqueline Kowtko

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

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 here 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.

Original language	English
Title of host publication	Proceedings of the Fourth International Conference on Spoken Language, 1996 (ICSLP `96)
Pages	216-219
Number of pages	4
Volume	1
DOIs	https://doi.org/10.1109/ICSLP.1996.607080
Publication status	Published - Oct 1996

Access to Document

10.1109/ICSLP.1996.607080

Cite this

@inproceedings{8592cbb770274d5785ef308a7e5f338b,

title = "Using Prosodic Information to Constrain Language Models for Spoken dialogue",

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 here 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.",

author = "Paul Taylor and Hiroshi Shimodaira and Stephen Isard and Simon King and Jacqueline Kowtko",

year = "1996",

month = oct,

doi = "10.1109/ICSLP.1996.607080",

language = "English",

isbn = "0780335554",

volume = "1",

pages = "216--219",

booktitle = "Proceedings of the Fourth International Conference on Spoken Language, 1996 (ICSLP `96)",

}

TY - GEN

T1 - Using Prosodic Information to Constrain Language Models for Spoken dialogue

AU - Taylor, Paul

AU - Shimodaira, Hiroshi

AU - Isard, Stephen

AU - King, Simon

AU - Kowtko, Jacqueline

PY - 1996/10

Y1 - 1996/10

N2 - 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 here 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.

AB - 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 here 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.

U2 - 10.1109/ICSLP.1996.607080

DO - 10.1109/ICSLP.1996.607080

M3 - Conference contribution

SN - 0780335554

VL - 1

SP - 216

EP - 219

BT - Proceedings of the Fourth International Conference on Spoken Language, 1996 (ICSLP `96)

ER -

Using Prosodic Information to Constrain Language Models for Spoken dialogue

Abstract / Description of output

Access to Document

Fingerprint

Cite this