Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

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

2 Citations (Scopus)

Abstract

In this paper, we propose a method of detecting task-incompleted users for a spoken dialog system using an N-gram-based dialog history model. We collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database was made by a field test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model was trained from sequences that consist of user dialog acts and/or system dialog acts for two dialog classes, that is, the dialog completed the music retrieval task or the dialog incompleted the task. Then the system detects unknown dialogs that is not completed the task based on the N-gram likelihood. Experiments were conducted on large real data, and the results show that our proposed method achieved good classification performance. When the classifier correctly detected all of the task-incompleted dialogs, our proposed method achieved a false detection rate of 6%.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Pages3034-3037
Number of pages4
Publication statusPublished - 2010
Externally publishedYes
Event11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan
Duration: Sep 26 2010Sep 30 2010

Other

Other11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
CountryJapan
CityMakuhari, Chiba
Period9/26/109/30/10

Fingerprint

Music
History
Databases
Spoken Dialogue Systems
N-gram
Dialogue Acts

Keywords

  • Dialog act
  • Dialog history
  • N-gram
  • Spoken dialog system

ASJC Scopus subject areas

  • Language and Linguistics
  • Speech and Hearing

Cite this

Hara, S., Kitaoka, N., & Takeda, K. (2010). Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 3034-3037)

Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram. / Hara, Sunao; Kitaoka, Norihide; Takeda, Kazuya.

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. p. 3034-3037.

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

Hara, S, Kitaoka, N & Takeda, K 2010, Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram. in Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. pp. 3034-3037, 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan, 9/26/10.
Hara S, Kitaoka N, Takeda K. Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. p. 3034-3037
Hara, Sunao ; Kitaoka, Norihide ; Takeda, Kazuya. / Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. pp. 3034-3037
@inproceedings{e660003e74c84dfdb154a4bbe627a1ac,
title = "Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram",
abstract = "In this paper, we propose a method of detecting task-incompleted users for a spoken dialog system using an N-gram-based dialog history model. We collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database was made by a field test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model was trained from sequences that consist of user dialog acts and/or system dialog acts for two dialog classes, that is, the dialog completed the music retrieval task or the dialog incompleted the task. Then the system detects unknown dialogs that is not completed the task based on the N-gram likelihood. Experiments were conducted on large real data, and the results show that our proposed method achieved good classification performance. When the classifier correctly detected all of the task-incompleted dialogs, our proposed method achieved a false detection rate of 6{\%}.",
keywords = "Dialog act, Dialog history, N-gram, Spoken dialog system",
author = "Sunao Hara and Norihide Kitaoka and Kazuya Takeda",
year = "2010",
language = "English",
pages = "3034--3037",
booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

}

TY - GEN

T1 - Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram

AU - Hara, Sunao

AU - Kitaoka, Norihide

AU - Takeda, Kazuya

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a method of detecting task-incompleted users for a spoken dialog system using an N-gram-based dialog history model. We collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database was made by a field test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model was trained from sequences that consist of user dialog acts and/or system dialog acts for two dialog classes, that is, the dialog completed the music retrieval task or the dialog incompleted the task. Then the system detects unknown dialogs that is not completed the task based on the N-gram likelihood. Experiments were conducted on large real data, and the results show that our proposed method achieved good classification performance. When the classifier correctly detected all of the task-incompleted dialogs, our proposed method achieved a false detection rate of 6%.

AB - In this paper, we propose a method of detecting task-incompleted users for a spoken dialog system using an N-gram-based dialog history model. We collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database was made by a field test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model was trained from sequences that consist of user dialog acts and/or system dialog acts for two dialog classes, that is, the dialog completed the music retrieval task or the dialog incompleted the task. Then the system detects unknown dialogs that is not completed the task based on the N-gram likelihood. Experiments were conducted on large real data, and the results show that our proposed method achieved good classification performance. When the classifier correctly detected all of the task-incompleted dialogs, our proposed method achieved a false detection rate of 6%.

KW - Dialog act

KW - Dialog history

KW - N-gram

KW - Spoken dialog system

UR - http://www.scopus.com/inward/record.url?scp=79959852228&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959852228&partnerID=8YFLogxK

M3 - Conference contribution

SP - 3034

EP - 3037

BT - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

ER -