Evaluation of a multi-speaker system for socially assistive HRI in real scenarios
Evaluation of a multi-speaker system for socially assistive HRI in real scenarios
In the field of social human-robot interaction, and in particular for social assistive robotics, the capacity of recognizing the speaker’s discourse in very diverse conditions and where more than one interlocutor may be present, plays an essential role. The use of a mics. array that can be mounted in a robot supported by a voice enhancement module has been evaluated, with the goal of improving the performance of current automatic speech recognition (ASR) systems in multi-speaker conditions. An evaluation has been made of the improvement in terms of intelligibility scores that can be achieved in the operation of two off-the-shelf ASR solutions in situations that contemplate the typical scenarios where a robot with these characteristics can be found. The results have identified the conditions in which a low computational cost demand algorithm can be beneficial to improve intelligibility scores in real environments.
Array, ASR, Beamforming, Intelligibility, Masking
151-166
Martínez-Colón, Antonio
90345d15-d871-4101-b01c-76c6081afc96
Viciana-Abad, Raquel
74ffc4e5-8e3e-4629-ba63-63128bf9fb43
Perez-Lorenzo, Jose Manuel
cc7f2fd6-1771-4526-9ab6-c601dd3eec13
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Naylor, Patrick A.
13079486-664a-414c-a1a2-01a30bf0997b
2021
Martínez-Colón, Antonio
90345d15-d871-4101-b01c-76c6081afc96
Viciana-Abad, Raquel
74ffc4e5-8e3e-4629-ba63-63128bf9fb43
Perez-Lorenzo, Jose Manuel
cc7f2fd6-1771-4526-9ab6-c601dd3eec13
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Naylor, Patrick A.
13079486-664a-414c-a1a2-01a30bf0997b
Martínez-Colón, Antonio, Viciana-Abad, Raquel, Perez-Lorenzo, Jose Manuel, Evers, Christine and Naylor, Patrick A.
(2021)
Evaluation of a multi-speaker system for socially assistive HRI in real scenarios.
Bergasa, Luis M., Ocaña, Manuel, Barea, Rafael, López-Guillén, Elena and Revenga, Pedro
(eds.)
In Advances in Physical Agents II. WAF 2020.
vol. 1285,
Springer.
.
(doi:10.1007/978-3-030-62579-5_11).
Record type:
Conference or Workshop Item
(Paper)
Abstract
In the field of social human-robot interaction, and in particular for social assistive robotics, the capacity of recognizing the speaker’s discourse in very diverse conditions and where more than one interlocutor may be present, plays an essential role. The use of a mics. array that can be mounted in a robot supported by a voice enhancement module has been evaluated, with the goal of improving the performance of current automatic speech recognition (ASR) systems in multi-speaker conditions. An evaluation has been made of the improvement in terms of intelligibility scores that can be achieved in the operation of two off-the-shelf ASR solutions in situations that contemplate the typical scenarios where a robot with these characteristics can be found. The results have identified the conditions in which a low computational cost demand algorithm can be beneficial to improve intelligibility scores in real environments.
This record has no associated files available for download.
More information
e-pub ahead of print date: 3 November 2020
Published date: 2021
Venue - Dates:
21st International Workshop of Physical Agents, WAF 2020, , Alcalá de Henares, Madrid, Spain, 2020-11-19 - 2020-11-20
Keywords:
Array, ASR, Beamforming, Intelligibility, Masking
Identifiers
Local EPrints ID: 446218
URI: http://eprints.soton.ac.uk/id/eprint/446218
ISSN: 2194-5357
PURE UUID: 1b01ee3a-f65f-46f5-9461-425c7e7a395a
Catalogue record
Date deposited: 29 Jan 2021 17:30
Last modified: 06 Jun 2024 02:08
Export record
Altmetrics
Contributors
Author:
Antonio Martínez-Colón
Author:
Raquel Viciana-Abad
Author:
Jose Manuel Perez-Lorenzo
Author:
Christine Evers
Author:
Patrick A. Naylor
Editor:
Luis M. Bergasa
Editor:
Manuel Ocaña
Editor:
Rafael Barea
Editor:
Elena López-Guillén
Editor:
Pedro Revenga
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics