{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/30182"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/30182","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Statistical modeling and analysis of audio-visual association in speech","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_html":"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_has_math":false,"creators":["Siracusa, Michael Richard, 1980-"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Trevor Darrell and John W. Fisher."],"committee_chairs":[],"committee_members":[],"year":2005,"date_issued":"2005","date_published":"2005","updated_at":"2026-07-22T22:22:02Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["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."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/30182","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Trevor Darrell and John W. Fisher."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Siracusa, Michael Richard, 1980-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2006-03-24T18:27:20Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2006-03-24T18:27:20Z"]},{"key":"dc:date.issued","label":"Date","values":["2005"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["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."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/30182"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2005.","Includes bibliographical references (p. 183-186)."]},{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Statistical modeling and analysis of audio-visual association in speech"]}]}],"canonical_facts":{"dc:contributor.advisor":["Trevor Darrell and John W. Fisher."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Siracusa, Michael Richard, 1980-"],"dc:date.accessioned":["2006-03-24T18:27:20Z"],"dc:date.available":["2006-03-24T18:27:20Z"],"dc:date.issued":["2005"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2005.","Includes bibliographical references (p. 183-186)."],"dc:description.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."],"dc:description.degree":["S.M."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["http://hdl.handle.net/1721.1/30182"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["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."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Statistical modeling and analysis of audio-visual association in speech"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:22:02Z"}