Selecting help messages by using robust grammar verification for handling out-of-grammar utterances in spoken dialogue systems

Kazunori Komatani, Yuichiro Fukubayashi, Satoshi Ikeda, Tetsuya Ogata, Hiroshi G. Okuno

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a weighted finite-state transducer, to accurately identify the grammar rule that the user intended to use for the utterance, even if important words are missing from the ASR results. We then use a ranking algorithm, RankBoost, to rank help message candidates in order of likely usefulness. Its features include the grammar verification results and the utterance history representing the user's experience.

Original languageEnglish
Pages (from-to)3359-3367
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE93-D
Issue number12
DOIs
Publication statusPublished - 2010 Dec
Externally publishedYes

Fingerprint

Speech recognition
Transducers

Keywords

  • Help generation
  • Novice user
  • Out-of-grammar utterances
  • Spoken dialogue system
  • Utterance history

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Selecting help messages by using robust grammar verification for handling out-of-grammar utterances in spoken dialogue systems. / Komatani, Kazunori; Fukubayashi, Yuichiro; Ikeda, Satoshi; Ogata, Tetsuya; Okuno, Hiroshi G.

In: IEICE Transactions on Information and Systems, Vol. E93-D, No. 12, 12.2010, p. 3359-3367.

Research output: Contribution to journalArticle

@article{72838c2a05ac4b47a170b1f7d2d3de8b,
title = "Selecting help messages by using robust grammar verification for handling out-of-grammar utterances in spoken dialogue systems",
abstract = "We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a weighted finite-state transducer, to accurately identify the grammar rule that the user intended to use for the utterance, even if important words are missing from the ASR results. We then use a ranking algorithm, RankBoost, to rank help message candidates in order of likely usefulness. Its features include the grammar verification results and the utterance history representing the user's experience.",
keywords = "Help generation, Novice user, Out-of-grammar utterances, Spoken dialogue system, Utterance history",
author = "Kazunori Komatani and Yuichiro Fukubayashi and Satoshi Ikeda and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2010",
month = "12",
doi = "10.1587/transinf.E93.D.3359",
language = "English",
volume = "E93-D",
pages = "3359--3367",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - Selecting help messages by using robust grammar verification for handling out-of-grammar utterances in spoken dialogue systems

AU - Komatani, Kazunori

AU - Fukubayashi, Yuichiro

AU - Ikeda, Satoshi

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2010/12

Y1 - 2010/12

N2 - We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a weighted finite-state transducer, to accurately identify the grammar rule that the user intended to use for the utterance, even if important words are missing from the ASR results. We then use a ranking algorithm, RankBoost, to rank help message candidates in order of likely usefulness. Its features include the grammar verification results and the utterance history representing the user's experience.

AB - We address the issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages. Help message generation for OOG utterances is a challenge because language understanding based on automatic speech recognition (ASR) of OOG utterances is usually erroneous; important words are often misrecognized or missing from such utterances. Our grammar verification method uses a weighted finite-state transducer, to accurately identify the grammar rule that the user intended to use for the utterance, even if important words are missing from the ASR results. We then use a ranking algorithm, RankBoost, to rank help message candidates in order of likely usefulness. Its features include the grammar verification results and the utterance history representing the user's experience.

KW - Help generation

KW - Novice user

KW - Out-of-grammar utterances

KW - Spoken dialogue system

KW - Utterance history

UR - http://www.scopus.com/inward/record.url?scp=78650028533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650028533&partnerID=8YFLogxK

U2 - 10.1587/transinf.E93.D.3359

DO - 10.1587/transinf.E93.D.3359

M3 - Article

VL - E93-D

SP - 3359

EP - 3367

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 12

ER -