{"id":"https://openalex.org/W2164450870","doi":"https://doi.org/10.1109/icassp.2002.5745027","title":"A coupled HMM for audio-visual speech recognition","display_name":"A coupled HMM for audio-visual speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2164450870","doi":"https://doi.org/10.1109/icassp.2002.5745027","mag":"2164450870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745027","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal 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/A5113481101","display_name":"Ara Nefian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ara V. Nefian","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052554057","display_name":"Luhong Liang","orcid":"https://orcid.org/0009-0001-4190-006X"},"institutions":[{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luhong Liang","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027964715","display_name":"Xiaobo Pi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Pi","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108103757","display_name":"Liu Xiao-xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu Xiaoxiang","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037496285","display_name":"Crusoe Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Crusoe Mao","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280100","display_name":"Kevin J. Murphy","orcid":"https://orcid.org/0009-0006-9681-3285"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Murphy","raw_affiliation_strings":["Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microcomputer Research Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113481101"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"],"apc_list":null,"apc_paid":null,"fwci":10.8822,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":{"value":0.99657827,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955000281333923,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8970974683761597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8078722953796387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762449979782104},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5290350317955017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4417887330055237},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448839485645294}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8970974683761597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8078722953796387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762449979782104},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5290350317955017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417887330055237},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448839485645294},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745027","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.134.2667","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.134.2667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ubc.ca/~murphyk/Papers/icassp02.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1576996184","https://openalex.org/W2015394094","https://openalex.org/W2083792893","https://openalex.org/W2099947851","https://openalex.org/W2121486117","https://openalex.org/W2129571380","https://openalex.org/W2152239535","https://openalex.org/W2171265988","https://openalex.org/W2799061466","https://openalex.org/W3099202502","https://openalex.org/W4205687621","https://openalex.org/W4205944311","https://openalex.org/W4297792526","https://openalex.org/W6671432306","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2033914206"],"abstract_inverted_index":{"In":[0],"recent":[1],"years":[2],"several":[3],"speech":[4,22,38,55,119],"recognition":[5,23,56],"systems":[6],"that":[7,46,68,108],"use":[8,26],"visual":[9,28,93,118],"together":[10],"with":[11],"audio":[12,91,117],"information":[13],"showed":[14],"significant":[15],"increase":[16],"in":[17,59,116],"performance":[18],"over":[19,102],"the":[20,34,37,42,80,86,90,109,113],"standard":[21],"systems.":[24],"The":[25,53,76,104],"of":[27,36,44,79,89],"features":[29,45],"is":[30],"justified":[31],"by":[32,41],"both":[33],"bimodality":[35],"generation":[39],"and":[40,92],"need":[43],"are":[47],"invariant":[48],"to":[49,84],"acoustic":[50],"noise":[51],"perturbation.":[52],"audio-visual":[54,65],"system":[57],"presented":[58],"this":[60],"paper":[61],"introduces":[62],"a":[63,70],"novel":[64],"fusion":[66],"technique":[67],"uses":[69],"coupled":[71,110],"hidden":[72],"Markov":[73],"model":[74,85],"(HMM).":[75],"statistical":[77],"properties":[78],"coupled-HMM":[81],"allow":[82],"us":[83],"state":[87],"asynchrony":[88],"observations":[94],"sequences":[95],"while":[96],"still":[97],"preserving":[98],"their":[99],"natural":[100],"correlation":[101],"time.":[103],"experimental":[105],"results":[106],"show":[107],"HMM":[111,115],"outperforms":[112],"multistream":[114],"recognition.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":16}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
