A spoken dialog system with redundant response to prevent user misunderstanding

Masaki Yamaoka, Sunao Hara, Masanobu Abe

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

Abstract

We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. Therefore, we need to solve the problems of user misunderstandings as well as misunderstanding of spoken dialog systems. For this purpose, we introduced a driver workload level in spoken dialog management in order to prevent user misunderstandings. A key strategy of the dialog management is to make speech redundant if the driver's workload is too high in assuming that the user probably misunderstand the system utterance under such a condition. An experiment was conducted to compare performances of the proposed method and a conventional method using a user simulator. The simulator is developed under the assumption of two types of drivers: an experienced driver model and a novice driver model. Experimental results showed that the proposed strategies achieved better performance than the conventional one for task completion time, task completion rate, and user's positive speech rate. In particular, these performance differences are greater for novice users than for experienced users.

Original languageEnglish
Title of host publication2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages223-226
Number of pages4
ISBN (Electronic)9789881476807
DOIs
Publication statusPublished - Feb 19 2016
Event2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong
Duration: Dec 16 2015Dec 19 2015

Other

Other2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
CountryHong Kong
CityHong Kong
Period12/16/1512/19/15

Fingerprint

Spoken Dialogue Systems
Simulators
Driver
Navigation systems
Dialogue Management
Railroad cars
Workload
Simulator
Experiments
Navigation System
Completion Time
Completion
Experimental Results
Model

ASJC Scopus subject areas

  • Artificial Intelligence
  • Modelling and Simulation
  • Signal Processing

Cite this

Yamaoka, M., Hara, S., & Abe, M. (2016). A spoken dialog system with redundant response to prevent user misunderstanding. In 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 (pp. 223-226). [7415511] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2015.7415511

A spoken dialog system with redundant response to prevent user misunderstanding. / Yamaoka, Masaki; Hara, Sunao; Abe, Masanobu.

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 223-226 7415511.

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

Yamaoka, M, Hara, S & Abe, M 2016, A spoken dialog system with redundant response to prevent user misunderstanding. in 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015., 7415511, Institute of Electrical and Electronics Engineers Inc., pp. 223-226, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015, Hong Kong, Hong Kong, 12/16/15. https://doi.org/10.1109/APSIPA.2015.7415511
Yamaoka M, Hara S, Abe M. A spoken dialog system with redundant response to prevent user misunderstanding. In 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 223-226. 7415511 https://doi.org/10.1109/APSIPA.2015.7415511
Yamaoka, Masaki ; Hara, Sunao ; Abe, Masanobu. / A spoken dialog system with redundant response to prevent user misunderstanding. 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 223-226
@inproceedings{f0a6334a449a4752b806b538a8b76e45,
title = "A spoken dialog system with redundant response to prevent user misunderstanding",
abstract = "We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. Therefore, we need to solve the problems of user misunderstandings as well as misunderstanding of spoken dialog systems. For this purpose, we introduced a driver workload level in spoken dialog management in order to prevent user misunderstandings. A key strategy of the dialog management is to make speech redundant if the driver's workload is too high in assuming that the user probably misunderstand the system utterance under such a condition. An experiment was conducted to compare performances of the proposed method and a conventional method using a user simulator. The simulator is developed under the assumption of two types of drivers: an experienced driver model and a novice driver model. Experimental results showed that the proposed strategies achieved better performance than the conventional one for task completion time, task completion rate, and user's positive speech rate. In particular, these performance differences are greater for novice users than for experienced users.",
author = "Masaki Yamaoka and Sunao Hara and Masanobu Abe",
year = "2016",
month = "2",
day = "19",
doi = "10.1109/APSIPA.2015.7415511",
language = "English",
pages = "223--226",
booktitle = "2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A spoken dialog system with redundant response to prevent user misunderstanding

AU - Yamaoka, Masaki

AU - Hara, Sunao

AU - Abe, Masanobu

PY - 2016/2/19

Y1 - 2016/2/19

N2 - We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. Therefore, we need to solve the problems of user misunderstandings as well as misunderstanding of spoken dialog systems. For this purpose, we introduced a driver workload level in spoken dialog management in order to prevent user misunderstandings. A key strategy of the dialog management is to make speech redundant if the driver's workload is too high in assuming that the user probably misunderstand the system utterance under such a condition. An experiment was conducted to compare performances of the proposed method and a conventional method using a user simulator. The simulator is developed under the assumption of two types of drivers: an experienced driver model and a novice driver model. Experimental results showed that the proposed strategies achieved better performance than the conventional one for task completion time, task completion rate, and user's positive speech rate. In particular, these performance differences are greater for novice users than for experienced users.

AB - We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. Therefore, we need to solve the problems of user misunderstandings as well as misunderstanding of spoken dialog systems. For this purpose, we introduced a driver workload level in spoken dialog management in order to prevent user misunderstandings. A key strategy of the dialog management is to make speech redundant if the driver's workload is too high in assuming that the user probably misunderstand the system utterance under such a condition. An experiment was conducted to compare performances of the proposed method and a conventional method using a user simulator. The simulator is developed under the assumption of two types of drivers: an experienced driver model and a novice driver model. Experimental results showed that the proposed strategies achieved better performance than the conventional one for task completion time, task completion rate, and user's positive speech rate. In particular, these performance differences are greater for novice users than for experienced users.

UR - http://www.scopus.com/inward/record.url?scp=84986222759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986222759&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2015.7415511

DO - 10.1109/APSIPA.2015.7415511

M3 - Conference contribution

AN - SCOPUS:84986222759

SP - 223

EP - 226

BT - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -