An adaptable task-oriented dialog system for stand-alone embedded devices

Long Duong, Vu Cong Duy Hoang, Tuyen Quang Pham, Yu-Heng Hong, Vladislavs Dovgalecs, Guy Bashkansky, Jason Black, Andrew Bleeker, Serge Le Huitouze, Mark Johnson

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

This paper describes a spoken-language end-to-end task-oriented dialogue system for small embedded devices such as home appliances. While the current system implements a smart alarm clock with advanced calendar scheduling functionality, the system is designed to make it easy to port to other application domains (e.g., the dialogue component factors out domain-specific execution from domain-general actions such as requesting and updating slot values). The system does not require internet connectivity because all components, including speech recognition, natural language understanding, dialogue management, execution and text-to-speech, run locally on the embedded device (our demo uses a Raspberry Pi). This simplifies deployment, minimizes server costs and most importantly, eliminates user privacy risks. The demo video in alarm domain is here youtu.be/N3IBMGocvHU
LanguageEnglish
Title of host publicationProceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publicationSystem Demonstrations
EditorsMarta R. Costa-jussà, Enrique Alfonseca
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics (ACL)
Pages49-57
Number of pages9
ISBN (Print)9781950737499
DOIs
Publication statusPublished - Jul 2019
Externally publishedYes
EventAnnual Meeting of the Association for Computational Linguistics (57th : 2019) - Florence, Italy
Duration: 28 Jul 20192 Aug 2019

Conference

ConferenceAnnual Meeting of the Association for Computational Linguistics (57th : 2019)
CountryItaly
CityFlorence
Period28/07/192/08/19

Fingerprint

Domestic appliances
Speech recognition
Clocks
Servers
Scheduling
Internet
Costs

Bibliographical note

Copyright the Publisher 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Cite this

Duong, L., Hoang, V. C. D., Pham, T. Q., Hong, Y-H., Dovgalecs, V., Bashkansky, G., ... Johnson, M. (2019). An adaptable task-oriented dialog system for stand-alone embedded devices. In M. R. Costa-jussà, & E. Alfonseca (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : System Demonstrations (pp. 49-57). Florence, Italy: Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P19-3009
Duong, Long ; Hoang, Vu Cong Duy ; Pham, Tuyen Quang ; Hong, Yu-Heng ; Dovgalecs, Vladislavs ; Bashkansky, Guy ; Black, Jason ; Bleeker, Andrew ; Huitouze, Serge Le ; Johnson, Mark. / An adaptable task-oriented dialog system for stand-alone embedded devices. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : System Demonstrations. editor / Marta R. Costa-jussà ; Enrique Alfonseca. Florence, Italy : Association for Computational Linguistics (ACL), 2019. pp. 49-57
@inproceedings{124c7c10e2d4442e989f730c5d125306,
title = "An adaptable task-oriented dialog system for stand-alone embedded devices",
abstract = "This paper describes a spoken-language end-to-end task-oriented dialogue system for small embedded devices such as home appliances. While the current system implements a smart alarm clock with advanced calendar scheduling functionality, the system is designed to make it easy to port to other application domains (e.g., the dialogue component factors out domain-specific execution from domain-general actions such as requesting and updating slot values). The system does not require internet connectivity because all components, including speech recognition, natural language understanding, dialogue management, execution and text-to-speech, run locally on the embedded device (our demo uses a Raspberry Pi). This simplifies deployment, minimizes server costs and most importantly, eliminates user privacy risks. The demo video in alarm domain is here youtu.be/N3IBMGocvHU",
author = "Long Duong and Hoang, {Vu Cong Duy} and Pham, {Tuyen Quang} and Yu-Heng Hong and Vladislavs Dovgalecs and Guy Bashkansky and Jason Black and Andrew Bleeker and Huitouze, {Serge Le} and Mark Johnson",
note = "Copyright the Publisher 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2019",
month = "7",
doi = "10.18653/v1/P19-3009",
language = "English",
isbn = "9781950737499",
pages = "49--57",
editor = "Costa-juss{\`a}, {Marta R.} and Enrique Alfonseca",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",

}

Duong, L, Hoang, VCD, Pham, TQ, Hong, Y-H, Dovgalecs, V, Bashkansky, G, Black, J, Bleeker, A, Huitouze, SL & Johnson, M 2019, An adaptable task-oriented dialog system for stand-alone embedded devices. in MR Costa-jussà & E Alfonseca (eds), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : System Demonstrations. Association for Computational Linguistics (ACL), Florence, Italy, pp. 49-57, Annual Meeting of the Association for Computational Linguistics (57th : 2019), Florence, Italy, 28/07/19. https://doi.org/10.18653/v1/P19-3009

An adaptable task-oriented dialog system for stand-alone embedded devices. / Duong, Long; Hoang, Vu Cong Duy; Pham, Tuyen Quang; Hong, Yu-Heng; Dovgalecs, Vladislavs; Bashkansky, Guy; Black, Jason; Bleeker, Andrew; Huitouze, Serge Le; Johnson, Mark.

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : System Demonstrations. ed. / Marta R. Costa-jussà; Enrique Alfonseca. Florence, Italy : Association for Computational Linguistics (ACL), 2019. p. 49-57.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - An adaptable task-oriented dialog system for stand-alone embedded devices

AU - Duong, Long

AU - Hoang, Vu Cong Duy

AU - Pham, Tuyen Quang

AU - Hong, Yu-Heng

AU - Dovgalecs, Vladislavs

AU - Bashkansky, Guy

AU - Black, Jason

AU - Bleeker, Andrew

AU - Huitouze, Serge Le

AU - Johnson, Mark

N1 - Copyright the Publisher 2019. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2019/7

Y1 - 2019/7

N2 - This paper describes a spoken-language end-to-end task-oriented dialogue system for small embedded devices such as home appliances. While the current system implements a smart alarm clock with advanced calendar scheduling functionality, the system is designed to make it easy to port to other application domains (e.g., the dialogue component factors out domain-specific execution from domain-general actions such as requesting and updating slot values). The system does not require internet connectivity because all components, including speech recognition, natural language understanding, dialogue management, execution and text-to-speech, run locally on the embedded device (our demo uses a Raspberry Pi). This simplifies deployment, minimizes server costs and most importantly, eliminates user privacy risks. The demo video in alarm domain is here youtu.be/N3IBMGocvHU

AB - This paper describes a spoken-language end-to-end task-oriented dialogue system for small embedded devices such as home appliances. While the current system implements a smart alarm clock with advanced calendar scheduling functionality, the system is designed to make it easy to port to other application domains (e.g., the dialogue component factors out domain-specific execution from domain-general actions such as requesting and updating slot values). The system does not require internet connectivity because all components, including speech recognition, natural language understanding, dialogue management, execution and text-to-speech, run locally on the embedded device (our demo uses a Raspberry Pi). This simplifies deployment, minimizes server costs and most importantly, eliminates user privacy risks. The demo video in alarm domain is here youtu.be/N3IBMGocvHU

U2 - 10.18653/v1/P19-3009

DO - 10.18653/v1/P19-3009

M3 - Conference proceeding contribution

SN - 9781950737499

SP - 49

EP - 57

BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

A2 - Costa-jussà, Marta R.

A2 - Alfonseca, Enrique

PB - Association for Computational Linguistics (ACL)

CY - Florence, Italy

ER -

Duong L, Hoang VCD, Pham TQ, Hong Y-H, Dovgalecs V, Bashkansky G et al. An adaptable task-oriented dialog system for stand-alone embedded devices. In Costa-jussà MR, Alfonseca E, editors, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics : System Demonstrations. Florence, Italy: Association for Computational Linguistics (ACL). 2019. p. 49-57 https://doi.org/10.18653/v1/P19-3009