Ask Alice: an Artificial Retrieval of Information Agent

Michel Valstar; Catherine Pelachaud; Dirk K.J. Heylen; Soumia Dermouche; Alexandru Ghitulescu; T. Baur; A. Cafaro; B. Potard; E. André; J. Wagner; L. Durieu; M. Aylett; E. Coutinho; B. Schuller; Yue Zhang; Mariet Theune; Jelte van Waterschoot

doi:10.1145/2993148.2998535

Ask Alice: an Artificial Retrieval of Information Agent

Michel Valstar, Catherine Pelachaud, Dirk K.J. Heylen, Soumia Dermouche, Alexandru Ghitulescu, T. Baur, A. Cafaro, B. Potard, E. André, J. Wagner, L. Durieu, M. Aylett, E. Coutinho, B. Schuller, Yue Zhang, Mariet Theune, Jelte van Waterschoot

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

19 Citations (Scopus)

52 Downloads (Pure)

Abstract

We present a demonstration of the ARIA framework, a modular approach for rapid development of virtual humans for information retrieval that have linguistic, emotional, and social skills and a strong personality. We demonstrate the capabilities of our framework in a scenario where a popular book from the English literature, ‘Alice in Wonderland’, is embodied by a virtual human called Alice. During the presentation one can engage in an information exchange dialogue, where Alice acts as the expert on the book, and the user as an interested novice. Besides speech recognition, sophisticated audio-visual behaviour analysis is used to inform the core agent dialogue module about the user’s state and intentions, so that it can go beyond simple chat-bot dialogue. The behaviour generation module features a unique new capability of being able to deal gracefully with interruptions of the agent.

Original language	English
Title of host publication	Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016
Place of Publication	New York
Publisher	Association for Computing Machinery
Pages	419-420
Number of pages	2
ISBN (Print)	978-1-4503-4556-9
DOIs	https://doi.org/10.1145/2993148.2998535
Publication status	Published - Nov 2016
Event	18th ACM International Conference on Multimodal Interaction, ICMI 2016 - Tokyo, Japan Duration: 12 Nov 2016 → 16 Nov 2016 Conference number: 18

Conference

Conference	18th ACM International Conference on Multimodal Interaction, ICMI 2016
Abbreviated title	ICMI
Country/Territory	Japan
City	Tokyo
Period	12/11/16 → 16/11/16

Access to Document

10.1145/2993148.2998535

19 Citations
1 PhD Thesis - Research UT, graduation UT

Personal and Personalized Conversations: Designing Agents Who Want To Connect With You
van Waterschoot, J. B., 2 Dec 2021, Enschede: University of Twente. 257 p.
Research output: Thesis › PhD Thesis - Research UT, graduation UT

Open Access
File
645 Downloads (Pure)

Cite this

Valstar, M., Pelachaud, C., Heylen, D. K. J., Dermouche, S., Ghitulescu, A., Baur, T., Cafaro, A., Potard, B., André, E., Wagner, J., Durieu, L., Aylett, M., Coutinho, E., Schuller, B., Zhang, Y., Theune, M., & van Waterschoot, J. (2016). Ask Alice: an Artificial Retrieval of Information Agent. In Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016 (pp. 419-420). Association for Computing Machinery. https://doi.org/10.1145/2993148.2998535

@inproceedings{15a05dc864454890bb7d5a227abd9fcd,

title = "Ask Alice: an Artificial Retrieval of Information Agent",

abstract = "We present a demonstration of the ARIA framework, a modular approach for rapid development of virtual humans for information retrieval that have linguistic, emotional, and social skills and a strong personality. We demonstrate the capabilities of our framework in a scenario where a popular book from the English literature, {\textquoteleft}Alice in Wonderland{\textquoteright}, is embodied by a virtual human called Alice. During the presentation one can engage in an information exchange dialogue, where Alice acts as the expert on the book, and the user as an interested novice. Besides speech recognition, sophisticated audio-visual behaviour analysis is used to inform the core agent dialogue module about the user{\textquoteright}s state and intentions, so that it can go beyond simple chat-bot dialogue. The behaviour generation module features a unique new capability of being able to deal gracefully with interruptions of the agent.",

author = "Michel Valstar and Catherine Pelachaud and Heylen, {Dirk K.J.} and Soumia Dermouche and Alexandru Ghitulescu and T. Baur and A. Cafaro and B. Potard and E. Andr{\'e} and J. Wagner and L. Durieu and M. Aylett and E. Coutinho and B. Schuller and Yue Zhang and Mariet Theune and {van Waterschoot}, Jelte",

year = "2016",

month = nov,

doi = "10.1145/2993148.2998535",

language = "English",

isbn = "978-1-4503-4556-9",

pages = "419--420",

booktitle = "Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016",

publisher = "Association for Computing Machinery",

address = "United States",

note = "18th ACM International Conference on Multimodal Interaction, ICMI 2016, ICMI ; Conference date: 12-11-2016 Through 16-11-2016",

}

Valstar, M, Pelachaud, C, Heylen, DKJ, Dermouche, S, Ghitulescu, A, Baur, T, Cafaro, A, Potard, B, André, E, Wagner, J, Durieu, L, Aylett, M, Coutinho, E, Schuller, B, Zhang, Y, Theune, M & van Waterschoot, J 2016, Ask Alice: an Artificial Retrieval of Information Agent. in Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016. Association for Computing Machinery, New York, pp. 419-420, 18th ACM International Conference on Multimodal Interaction, ICMI 2016, Tokyo, Japan, 12/11/16. https://doi.org/10.1145/2993148.2998535

Ask Alice: an Artificial Retrieval of Information Agent. / Valstar, Michel; Pelachaud, Catherine; Heylen, Dirk K.J. et al.
Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016. New York: Association for Computing Machinery, 2016. p. 419-420.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Ask Alice

T2 - 18th ACM International Conference on Multimodal Interaction, ICMI 2016

AU - Valstar, Michel

AU - Pelachaud, Catherine

AU - Heylen, Dirk K.J.

AU - Dermouche, Soumia

AU - Ghitulescu, Alexandru

AU - Baur, T.

AU - Cafaro, A.

AU - Potard, B.

AU - André, E.

AU - Wagner, J.

AU - Durieu, L.

AU - Aylett, M.

AU - Coutinho, E.

AU - Schuller, B.

AU - Zhang, Yue

AU - Theune, Mariet

AU - van Waterschoot, Jelte

N1 - Conference code: 18

PY - 2016/11

Y1 - 2016/11

N2 - We present a demonstration of the ARIA framework, a modular approach for rapid development of virtual humans for information retrieval that have linguistic, emotional, and social skills and a strong personality. We demonstrate the capabilities of our framework in a scenario where a popular book from the English literature, ‘Alice in Wonderland’, is embodied by a virtual human called Alice. During the presentation one can engage in an information exchange dialogue, where Alice acts as the expert on the book, and the user as an interested novice. Besides speech recognition, sophisticated audio-visual behaviour analysis is used to inform the core agent dialogue module about the user’s state and intentions, so that it can go beyond simple chat-bot dialogue. The behaviour generation module features a unique new capability of being able to deal gracefully with interruptions of the agent.

AB - We present a demonstration of the ARIA framework, a modular approach for rapid development of virtual humans for information retrieval that have linguistic, emotional, and social skills and a strong personality. We demonstrate the capabilities of our framework in a scenario where a popular book from the English literature, ‘Alice in Wonderland’, is embodied by a virtual human called Alice. During the presentation one can engage in an information exchange dialogue, where Alice acts as the expert on the book, and the user as an interested novice. Besides speech recognition, sophisticated audio-visual behaviour analysis is used to inform the core agent dialogue module about the user’s state and intentions, so that it can go beyond simple chat-bot dialogue. The behaviour generation module features a unique new capability of being able to deal gracefully with interruptions of the agent.

U2 - 10.1145/2993148.2998535

DO - 10.1145/2993148.2998535

M3 - Conference contribution

SN - 978-1-4503-4556-9

SP - 419

EP - 420

BT - Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016

PB - Association for Computing Machinery

CY - New York

Y2 - 12 November 2016 through 16 November 2016

ER -

Ask Alice: an Artificial Retrieval of Information Agent

Abstract

Conference

Access to Document

Fingerprint

Research output

Personal and Personalized Conversations: Designing Agents Who Want To Connect With You

Cite this