Ask Alice: an artificial retrieval of information agent

Michel Valstar; Tobias Baur; Angelo Cafaro; Alexandru Ghitulescu; Blaise Potard; Johannes Wagner; Elisabeth André; Laurent Durieu; Matthew Aylett; Soumia Dermouche; Catherine Pelachaud; Björn Schuller; Yue Zhang; Dirk Heylen; Mariët Theune; Jelte van Waterschoot

doi:10.1145/2993148.299853

Ask Alice: an artificial retrieval of information agent

Michel Valstar, Tobias Baur, Angelo Cafaro, Alexandru Ghitulescu, Blaise Potard, Johannes Wagner, Elisabeth André, Laurent Durieu, Matthew Aylett, Soumia Dermouche, Catherine Pelachaud, Björn Schuller, Yue Zhang, Dirk Heylen, Mariët Theune, Jelte van Waterschoot

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

19 Citations (Scopus)

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 framework's capabilities in a scenario where `Alice in Wonderland', a popular English literature book, is embodied by a virtual human representing Alice. The user 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
Publisher	Association for Computing Machinery
Pages	419-420
Number of pages	2
ISBN (Print)	9781450345569
DOIs	https://doi.org/10.1145/2993148.299853
Publication status	Published - 31 Oct 2016

Access to Document

10.1145/2993148.299853

Cite this

Valstar, M., Baur, T., Cafaro, A., Ghitulescu, A., Potard, B., Wagner, J., André, E., Durieu, L., Aylett, M., Dermouche, S., Pelachaud, C., Schuller, B., Zhang, Y., Heylen, D., 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 (pp. 419-420). Association for Computing Machinery. https://doi.org/10.1145/2993148.299853

@inproceedings{179e1073abef4c499f5c1878faccd1c3,

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 framework's capabilities in a scenario where `Alice in Wonderland', a popular English literature book, is embodied by a virtual human representing Alice. The user 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.",

author = "Michel Valstar and Tobias Baur and Angelo Cafaro and Alexandru Ghitulescu and Blaise Potard and Johannes Wagner and Elisabeth Andr{\'e} and Laurent Durieu and Matthew Aylett and Soumia Dermouche and Catherine Pelachaud and Bj{\"o}rn Schuller and Yue Zhang and Dirk Heylen and Mari{\"e}t Theune and {van Waterschoot}, Jelte",

year = "2016",

month = oct,

day = "31",

doi = "10.1145/2993148.299853",

language = "English",

isbn = "9781450345569",

pages = "419--420",

booktitle = "Proceedings of the 18th ACM international conference on multimodal interaction",

publisher = "Association for Computing Machinery",

address = "United States",

}

Valstar, M, Baur, T, Cafaro, A, Ghitulescu, A, Potard, B, Wagner, J, André, E, Durieu, L, Aylett, M, Dermouche, S, Pelachaud, C, Schuller, B, Zhang, Y, Heylen, D, 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. Association for Computing Machinery, pp. 419-420. https://doi.org/10.1145/2993148.299853

TY - GEN

T1 - Ask Alice: an artificial retrieval of information agent

AU - Valstar, Michel

AU - Baur, Tobias

AU - Cafaro, Angelo

AU - Ghitulescu, Alexandru

AU - Potard, Blaise

AU - Wagner, Johannes

AU - André, Elisabeth

AU - Durieu, Laurent

AU - Aylett, Matthew

AU - Dermouche, Soumia

AU - Pelachaud, Catherine

AU - Schuller, Björn

AU - Zhang, Yue

AU - Heylen, Dirk

AU - Theune, Mariët

AU - van Waterschoot, Jelte

PY - 2016/10/31

Y1 - 2016/10/31

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 framework's capabilities in a scenario where `Alice in Wonderland', a popular English literature book, is embodied by a virtual human representing Alice. The user 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 framework's capabilities in a scenario where `Alice in Wonderland', a popular English literature book, is embodied by a virtual human representing Alice. The user 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 - 10.1145/2993148.299853

DO - 10.1145/2993148.299853

M3 - Conference contribution

SN - 9781450345569

SP - 419

EP - 420

BT - Proceedings of the 18th ACM international conference on multimodal interaction

PB - Association for Computing Machinery

ER -

Ask Alice: an artificial retrieval of information agent

Abstract

Access to Document

Fingerprint

Cite this