{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/81062"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/81062","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Probabilistic Correspondence Mapping for Audiovisual Speaker Modeling","abstract":"In addition to the framework of probabilistic correspondence mapping on audiovisual speaker modeling, we also explore the correspondence problems with different constraints. Frequency domain correspondence between speakers is established via dynamic programming for speaker normalization in speech recognition tasks. The adjacent constraints in frequency domain actually help to stabilize the algorithm, similar to the dynamic time warping techniques. We also explore the correspondence problem given the manifold structure of different pose face images. It turns out that the manifold structure is very useful to build a good correspondence across different subjects. For audiovisual fusion, a new fusion scheme factorizes audio and visual features into correlated and uncorrelated ones. The correlated features are considered to be the correspondence between two modalities.","abstract_html":"In addition to the framework of probabilistic correspondence mapping on audiovisual speaker modeling, we also explore the correspondence problems with different constraints. Frequency domain correspondence between speakers is established via dynamic programming for speaker normalization in speech recognition tasks. The adjacent constraints in frequency domain actually help to stabilize the algorithm, similar to the dynamic time warping techniques. We also explore the correspondence problem given the manifold structure of different pose face images. It turns out that the manifold structure is very useful to build a good correspondence across different subjects. For audiovisual fusion, a new fusion scheme factorizes audio and visual features into correlated and uncorrelated ones. The correlated features are considered to be the correspondence between two modalities.","abstract_has_math":false,"creators":["Liu, Ming"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Thomas Huang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-09-25T20:09:27Z","date_published":"2015-09-25T20:09:27Z","updated_at":"2026-07-22T22:26:15Z","subjects":["Engineering, Electronics and Electrical"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(MiAaPQ)AAI3301186"],"render_values":[{"text":"(MiAaPQ)AAI3301186","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/81062","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Thomas Huang"]},{"key":"dc:creator","label":"Author","values":["Liu, Ming"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-09-25T20:09:27Z","10000-01-01","2007"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering, Electronics and Electrical"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/81062","(MiAaPQ)AAI3301186"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In addition to the framework of probabilistic correspondence mapping on audiovisual speaker modeling, we also explore the correspondence problems with different constraints. Frequency domain correspondence between speakers is established via dynamic programming for speaker normalization in speech recognition tasks. The adjacent constraints in frequency domain actually help to stabilize the algorithm, similar to the dynamic time warping techniques. We also explore the correspondence problem given the manifold structure of different pose face images. It turns out that the manifold structure is very useful to build a good correspondence across different subjects. For audiovisual fusion, a new fusion scheme factorizes audio and visual features into correlated and uncorrelated ones. The correlated features are considered to be the correspondence between two modalities.","Made available in DSpace on 2015-09-25T20:09:27Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3301186.pdf: 2612824 bytes, checksum: fb66d3965272351bbf71670a23fec945 (MD5) Previous issue date: 2007","Embargo set by: Seth Robbins for item 82344 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","91 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007."]},{"key":"dc:title","label":"Title","values":["Probabilistic Correspondence Mapping for Audiovisual Speaker Modeling"]}]}],"canonical_facts":{"dc:contributor":["Thomas Huang"],"dc:creator":["Liu, Ming"],"dc:date":["2015-09-25T20:09:27Z","10000-01-01","2007"],"dc:description":["In addition to the framework of probabilistic correspondence mapping on audiovisual speaker modeling, we also explore the correspondence problems with different constraints. Frequency domain correspondence between speakers is established via dynamic programming for speaker normalization in speech recognition tasks. The adjacent constraints in frequency domain actually help to stabilize the algorithm, similar to the dynamic time warping techniques. We also explore the correspondence problem given the manifold structure of different pose face images. It turns out that the manifold structure is very useful to build a good correspondence across different subjects. For audiovisual fusion, a new fusion scheme factorizes audio and visual features into correlated and uncorrelated ones. The correlated features are considered to be the correspondence between two modalities.","Made available in DSpace on 2015-09-25T20:09:27Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3301186.pdf: 2612824 bytes, checksum: fb66d3965272351bbf71670a23fec945 (MD5) Previous issue date: 2007","Embargo set by: Seth Robbins for item 82344 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","91 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007."],"dc:identifier":["http://hdl.handle.net/2142/81062","(MiAaPQ)AAI3301186"],"dc:language":["eng"],"dc:subject":["Engineering, Electronics and Electrical"],"dc:title":["Probabilistic Correspondence Mapping for Audiovisual Speaker Modeling"],"dc:type":["text"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:15Z"}