{"id":"https://openalex.org/W2149915648","doi":"https://doi.org/10.1109/icip.2002.1038188","title":"Bimodal fusion in audio-visual speech recognition","display_name":"Bimodal fusion in audio-visual speech recognition","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2149915648","doi":"https://doi.org/10.1109/icip.2002.1038188","mag":"2149915648"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2002.1038188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2002.1038188","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. International Conference on Image Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826189","display_name":"Xiaozheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaozheng Zhang","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110449498","display_name":"R.M. Mersereau","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.M. Mersereau","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039007664","display_name":"M. Clements","orcid":"https://orcid.org/0000-0001-7371-1012"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Clements","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101826189"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.5926,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70275108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7882782220840454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7838848829269409},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7811414003372192},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7757683992385864},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5960621237754822},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4760558307170868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4647855758666992},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4626404345035553},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.456043541431427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3787330389022827},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08123856782913208}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7882782220840454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838848829269409},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7811414003372192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7757683992385864},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5960621237754822},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4760558307170868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4647855758666992},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4626404345035553},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.456043541431427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3787330389022827},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08123856782913208},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icip.2002.1038188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2002.1038188","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. International Conference on Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.calpoly.edu:eeng_fac-1262","is_oa":false,"landing_page_url":"https://digitalcommons.calpoly.edu/eeng_fac/262","pdf_url":null,"source":{"id":"https://openalex.org/S4377196328","display_name":"DigitalCommons - CalPoly (California State Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98947143","host_organization_name":"California State Polytechnic University","host_organization_lineage":["https://openalex.org/I98947143"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical Engineering","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.875.2431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.875.2431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article%3D1262%26context%3Deeng_fac","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W88081813","https://openalex.org/W991614603","https://openalex.org/W1575388622","https://openalex.org/W2042732685","https://openalex.org/W2049073556","https://openalex.org/W2080630878","https://openalex.org/W2106844098","https://openalex.org/W2108492645","https://openalex.org/W2132297779","https://openalex.org/W2132588110","https://openalex.org/W2487271655","https://openalex.org/W2979006918","https://openalex.org/W3040607653","https://openalex.org/W3099202502","https://openalex.org/W3179102351","https://openalex.org/W6603616073","https://openalex.org/W6634449904","https://openalex.org/W6662700961","https://openalex.org/W6679860565","https://openalex.org/W6768650569","https://openalex.org/W6780461992","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Extending":[0],"automatic":[1],"speech":[2,47],"recognition":[3,14],"(ASR)":[4],"to":[5,12,39,49,83],"the":[6,41,45,58,74,92,116],"visual":[7,42,61],"modality":[8],"has":[9],"been":[10],"shown":[11],"increase":[13],"accuracy":[15],"greatly":[16],"and":[17,60,72,107],"improve":[18],"system":[19],"robustness":[20],"over":[21],"purely":[22],"acoustic":[23,46,104],"systems,":[24],"especially":[25],"in":[26],"acoustically":[27],"hostile":[28],"environments.":[29],"An":[30],"important":[31],"aspect":[32],"of":[33,56,76,103,119],"designing":[34],"such":[35],"systems":[36],"is":[37],"how":[38],"incorporate":[40],"component":[43],"into":[44],"recognizer":[48],"achieve":[50],"optimal":[51],"performance.":[52],"We":[53,67],"investigate":[54],"methods":[55],"integrating":[57],"audio":[59],"modalities":[62],"within":[63],"HMM-based":[64],"classification":[65],"models.":[66],"examine":[68],"existing":[69],"integration":[70,97],"schemes":[71],"propose":[73],"use":[75],"a":[77,100],"coupled":[78],"hidden":[79],"Markov":[80],"model":[81],"(CHMM)":[82],"exploit":[84],"audio-visual":[85],"interaction.":[86],"Our":[87],"experimental":[88],"results":[89],"demonstrate":[90],"that":[91,109],"CHMM":[93],"consistently":[94],"outperforms":[95],"other":[96],"models":[98],"for":[99],"large":[101],"range":[102],"noise":[105],"levels":[106],"suggest":[108],"it":[110],"better":[111],"captures":[112],"temporal":[113],"correlations":[114],"between":[115],"two":[117],"streams":[118],"information.":[120]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}