Analyzing temporal transition of real user's behaviors in a spoken dialogue system

Kazunori Komatani, Tatsuya Kawahara, Hiroshi G. Okuno

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

2 Citations (Scopus)

Abstract

Managing various behaviors of real users is indispensable for spoken dialogue systems to operate adequately in real environments. We have analyzed various users' behaviors using data collected over 34 months from the Kyoto City Bus Information System. We focused on "barge-in" and added barge-in rates to our analysis. Temporal transitions of users' behaviors, such as automatic speech recognition (ASR) accuracy, task success rates and barge-in rates, were initially investigated. We then examined the relationship between ASR accuracy and barge-in rates. Analysis revealed that the ASR accuracy of utterances inputted with barge-ins was lower because many novices, who were not accustomed to the timing when to utter, used the system. We also observed that the ASR accuracy of utterances with barge-ins differed based on the barge-in rates of individual users. The results indicate that the barge-in rate can be used as a novel user profile for detecting ASR errors.

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages1837-1840
Number of pages4
Volume3
Publication statusPublished - 2007
Externally publishedYes
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp
Duration: 2007 Aug 272007 Aug 31

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CityAntwerp
Period07/8/2707/8/31

Fingerprint

Spoken Dialogue Systems
Automatic Speech Recognition
Barges
User Behavior
communication technology
Speech recognition
User Profile
Information Systems
Timing
information system
Information systems

Keywords

  • Baree-in
  • Real user behavior
  • Spoken dialogue system

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modelling and Simulation
  • Linguistics and Language
  • Communication

Cite this

Komatani, K., Kawahara, T., & Okuno, H. G. (2007). Analyzing temporal transition of real user's behaviors in a spoken dialogue system. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007 (Vol. 3, pp. 1837-1840)

Analyzing temporal transition of real user's behaviors in a spoken dialogue system. / Komatani, Kazunori; Kawahara, Tatsuya; Okuno, Hiroshi G.

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3 2007. p. 1837-1840.

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

Komatani, K, Kawahara, T & Okuno, HG 2007, Analyzing temporal transition of real user's behaviors in a spoken dialogue system. in International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. vol. 3, pp. 1837-1840, 8th Annual Conference of the International Speech Communication Association, Interspeech 2007, Antwerp, 07/8/27.
Komatani K, Kawahara T, Okuno HG. Analyzing temporal transition of real user's behaviors in a spoken dialogue system. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3. 2007. p. 1837-1840
Komatani, Kazunori ; Kawahara, Tatsuya ; Okuno, Hiroshi G. / Analyzing temporal transition of real user's behaviors in a spoken dialogue system. International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3 2007. pp. 1837-1840
@inproceedings{a151f8751691413784ede09a82d88c76,
title = "Analyzing temporal transition of real user's behaviors in a spoken dialogue system",
abstract = "Managing various behaviors of real users is indispensable for spoken dialogue systems to operate adequately in real environments. We have analyzed various users' behaviors using data collected over 34 months from the Kyoto City Bus Information System. We focused on {"}barge-in{"} and added barge-in rates to our analysis. Temporal transitions of users' behaviors, such as automatic speech recognition (ASR) accuracy, task success rates and barge-in rates, were initially investigated. We then examined the relationship between ASR accuracy and barge-in rates. Analysis revealed that the ASR accuracy of utterances inputted with barge-ins was lower because many novices, who were not accustomed to the timing when to utter, used the system. We also observed that the ASR accuracy of utterances with barge-ins differed based on the barge-in rates of individual users. The results indicate that the barge-in rate can be used as a novel user profile for detecting ASR errors.",
keywords = "Baree-in, Real user behavior, Spoken dialogue system",
author = "Kazunori Komatani and Tatsuya Kawahara and Okuno, {Hiroshi G.}",
year = "2007",
language = "English",
isbn = "9781605603162",
volume = "3",
pages = "1837--1840",
booktitle = "International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007",

}

TY - GEN

T1 - Analyzing temporal transition of real user's behaviors in a spoken dialogue system

AU - Komatani, Kazunori

AU - Kawahara, Tatsuya

AU - Okuno, Hiroshi G.

PY - 2007

Y1 - 2007

N2 - Managing various behaviors of real users is indispensable for spoken dialogue systems to operate adequately in real environments. We have analyzed various users' behaviors using data collected over 34 months from the Kyoto City Bus Information System. We focused on "barge-in" and added barge-in rates to our analysis. Temporal transitions of users' behaviors, such as automatic speech recognition (ASR) accuracy, task success rates and barge-in rates, were initially investigated. We then examined the relationship between ASR accuracy and barge-in rates. Analysis revealed that the ASR accuracy of utterances inputted with barge-ins was lower because many novices, who were not accustomed to the timing when to utter, used the system. We also observed that the ASR accuracy of utterances with barge-ins differed based on the barge-in rates of individual users. The results indicate that the barge-in rate can be used as a novel user profile for detecting ASR errors.

AB - Managing various behaviors of real users is indispensable for spoken dialogue systems to operate adequately in real environments. We have analyzed various users' behaviors using data collected over 34 months from the Kyoto City Bus Information System. We focused on "barge-in" and added barge-in rates to our analysis. Temporal transitions of users' behaviors, such as automatic speech recognition (ASR) accuracy, task success rates and barge-in rates, were initially investigated. We then examined the relationship between ASR accuracy and barge-in rates. Analysis revealed that the ASR accuracy of utterances inputted with barge-ins was lower because many novices, who were not accustomed to the timing when to utter, used the system. We also observed that the ASR accuracy of utterances with barge-ins differed based on the barge-in rates of individual users. The results indicate that the barge-in rate can be used as a novel user profile for detecting ASR errors.

KW - Baree-in

KW - Real user behavior

KW - Spoken dialogue system

UR - http://www.scopus.com/inward/record.url?scp=56149100545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149100545&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56149100545

SN - 9781605603162

VL - 3

SP - 1837

EP - 1840

BT - International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

ER -