No Cover Image

Conference Paper/Proceeding/Abstract 1023 views

Acoustic and facial features for speaker recognition

Matt Roach Orcid Logo, J.D. Brand, J.S.D. Mason

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

Swansea University Author: Matt Roach Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1109/icpr.2000.903534

Abstract

This paper gives an insight into biometrics used for speaker recognition. Three different biometrics are presented, based on: acoustic, geometric lip, and holistic facial features. Experiments are carried out using a corpus of the DAVID audio-visual database. Recognition accuracy is found to be simi...

Full description

Published in: Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
Published: IEEE Comput. Soc 2002
Online Access: http://dx.doi.org/10.1109/icpr.2000.903534
URI: https://cronfa.swan.ac.uk/Record/cronfa39141
first_indexed 2018-03-22T05:12:37Z
last_indexed 2024-11-14T11:47:33Z
id cronfa39141
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-05-22T14:59:51.8275538</datestamp><bib-version>v2</bib-version><id>39141</id><entry>2018-03-21</entry><title>Acoustic and facial features for speaker recognition</title><swanseaauthors><author><sid>9722c301d5bbdc96e967cdc629290fec</sid><ORCID>0000-0002-1486-5537</ORCID><firstname>Matt</firstname><surname>Roach</surname><name>Matt Roach</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-03-21</date><deptcode>MACS</deptcode><abstract>This paper gives an insight into biometrics used for speaker recognition. Three different biometrics are presented, based on: acoustic, geometric lip, and holistic facial features. Experiments are carried out using a corpus of the DAVID audio-visual database. Recognition accuracy is found to be similar in the 2 domains. The geometric visual feature is based on a method of signature coding of the contour of the lips and the holistic feature is based on a mean dynamic signature, a method of capturing the motions of the face during a spoken utterance. Physical biometrics (static measurements) demand only small model sizes, perhaps just a single template, and therefore require less training data. Conversely behavioral biometrics contain more variation and demand more training data</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings 15th International Conference on Pattern Recognition. ICPR-2000</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>IEEE Comput. Soc</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>6</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2002</publishedYear><publishedDate>2002-08-06</publishedDate><doi>10.1109/icpr.2000.903534</doi><url>http://dx.doi.org/10.1109/icpr.2000.903534</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-05-22T14:59:51.8275538</lastEdited><Created>2018-03-21T20:19:50.6269491</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Matt</firstname><surname>Roach</surname><orcid>0000-0002-1486-5537</orcid><order>1</order></author><author><firstname>J.D.</firstname><surname>Brand</surname><order>2</order></author><author><firstname>J.S.D.</firstname><surname>Mason</surname><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2023-05-22T14:59:51.8275538 v2 39141 2018-03-21 Acoustic and facial features for speaker recognition 9722c301d5bbdc96e967cdc629290fec 0000-0002-1486-5537 Matt Roach Matt Roach true false 2018-03-21 MACS This paper gives an insight into biometrics used for speaker recognition. Three different biometrics are presented, based on: acoustic, geometric lip, and holistic facial features. Experiments are carried out using a corpus of the DAVID audio-visual database. Recognition accuracy is found to be similar in the 2 domains. The geometric visual feature is based on a method of signature coding of the contour of the lips and the holistic feature is based on a mean dynamic signature, a method of capturing the motions of the face during a spoken utterance. Physical biometrics (static measurements) demand only small model sizes, perhaps just a single template, and therefore require less training data. Conversely behavioral biometrics contain more variation and demand more training data Conference Paper/Proceeding/Abstract Proceedings 15th International Conference on Pattern Recognition. ICPR-2000 IEEE Comput. Soc 6 8 2002 2002-08-06 10.1109/icpr.2000.903534 http://dx.doi.org/10.1109/icpr.2000.903534 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2023-05-22T14:59:51.8275538 2018-03-21T20:19:50.6269491 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Matt Roach 0000-0002-1486-5537 1 J.D. Brand 2 J.S.D. Mason 3
title Acoustic and facial features for speaker recognition
spellingShingle Acoustic and facial features for speaker recognition
Matt Roach
title_short Acoustic and facial features for speaker recognition
title_full Acoustic and facial features for speaker recognition
title_fullStr Acoustic and facial features for speaker recognition
title_full_unstemmed Acoustic and facial features for speaker recognition
title_sort Acoustic and facial features for speaker recognition
author_id_str_mv 9722c301d5bbdc96e967cdc629290fec
author_id_fullname_str_mv 9722c301d5bbdc96e967cdc629290fec_***_Matt Roach
author Matt Roach
author2 Matt Roach
J.D. Brand
J.S.D. Mason
format Conference Paper/Proceeding/Abstract
container_title Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
publishDate 2002
institution Swansea University
doi_str_mv 10.1109/icpr.2000.903534
publisher IEEE Comput. Soc
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.1109/icpr.2000.903534
document_store_str 0
active_str 0
description This paper gives an insight into biometrics used for speaker recognition. Three different biometrics are presented, based on: acoustic, geometric lip, and holistic facial features. Experiments are carried out using a corpus of the DAVID audio-visual database. Recognition accuracy is found to be similar in the 2 domains. The geometric visual feature is based on a method of signature coding of the contour of the lips and the holistic feature is based on a mean dynamic signature, a method of capturing the motions of the face during a spoken utterance. Physical biometrics (static measurements) demand only small model sizes, perhaps just a single template, and therefore require less training data. Conversely behavioral biometrics contain more variation and demand more training data
published_date 2002-08-06T19:22:22Z
_version_ 1821343946117218304
score 11.04748

Similar Items