2026-09-18T22:31:09Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/301822022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Trevor Darrell and John W. Fisher.
Siracusa, Michael Richard, 1980-
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2006-03-24T18:27:20Z
2006-03-24T18:27:20Z
2004
2005
http://hdl.handle.net/1721.1/30182
60679852
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2005.
Includes bibliographical references (p. 183-186).
Currently, most dialog systems are restricted to single user environments. This thesis aims to promote an un-tethered multi-person dialog system by exploring approaches to help solve the speech correspondence problem (i.e. who, if anyone, is currently speaking). We adopt a statistical framework in which this problem is put in the form of a hypothesis test and focus on the subtask of discriminating between associated and non-associated audio-visual observations. Various methods for modeling our audio-visual observations and ways of carrying out this test are studied and their relative performance is compared. We discuss issues that arise from the inherently high dimensional nature of audio-visual data and address these issues by exploring different techniques for finding low-dimensional informative subspaces in which we can perform our hypothesis tests. We study our ability to learn a person-specific as well as a generic model for measuring audio-visual association and evaluate performance oil multiple subjects taken from MIT's AVTIMIT database.
by Michael Richard Siracusa.
S.M.
186 p.
8400105 bytes
8423575 bytes
application/pdf
application/pdf
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Statistical modeling and analysis of audio-visual association in speech
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b73e635c-1716-4d7f-afd2-a965ed2cb887">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Statistical modeling and analysis of audio-visual association in speech</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2005</PublicationDate>
<Authors>
<Author>
<DisplayName>Siracusa, Michael Richard, 1980-</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Currently, most dialog systems are restricted to single user environments. This thesis aims to promote an un-tethered multi-person dialog system by exploring approaches to help solve the speech correspondence problem (i.e. who, if anyone, is currently speaking). We adopt a statistical framework in which this problem is put in the form of a hypothesis test and focus on the subtask of discriminating between associated and non-associated audio-visual observations. Various methods for modeling our audio-visual observations and ways of carrying out this test are studied and their relative performance is compared. We discuss issues that arise from the inherently high dimensional nature of audio-visual data and address these issues by exploring different techniques for finding low-dimensional informative subspaces in which we can perform our hypothesis tests. We study our ability to learn a person-specific as well as a generic model for measuring audio-visual association and evaluate performance oil multiple subjects taken from MIT's AVTIMIT database.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>