{"id":"https://openalex.org/W2121551559","doi":"https://doi.org/10.1109/icassp.2003.1198707","title":"Frame-dependent multi-stream reliability indicators for audio-visual speech recognition","display_name":"Frame-dependent multi-stream reliability indicators for audio-visual speech recognition","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2121551559","doi":"https://doi.org/10.1109/icassp.2003.1198707","mag":"2121551559"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198707","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5002107058","display_name":"A. Garg","orcid":"https://orcid.org/0000-0001-9155-4794"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Garg","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA","Beckman Institute , University of Illinois , Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute , University of Illinois , Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Potamianos","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111579153","display_name":"C. Neti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Neti","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457343","display_name":"T.S. Huang","orcid":"https://orcid.org/0000-0003-1513-1356"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA","Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1111,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93293592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"24"},"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":0.9994999766349792,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7012521624565125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686307787895203},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6016518473625183},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48100385069847107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45220470428466797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45217376947402954},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4235076308250427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11616578698158264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012521624565125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686307787895203},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6016518473625183},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48100385069847107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45220470428466797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45217376947402954},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4235076308250427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11616578698158264},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1198707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198707","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.7509","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.7509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/AVSTG/ICASSP03_RELIABILITY.pdf","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":17,"referenced_works":["https://openalex.org/W1520736967","https://openalex.org/W1523010034","https://openalex.org/W1529401398","https://openalex.org/W1978380426","https://openalex.org/W2015394094","https://openalex.org/W2083792893","https://openalex.org/W2121430128","https://openalex.org/W2121486117","https://openalex.org/W2125838338","https://openalex.org/W2133115605","https://openalex.org/W2153606381","https://openalex.org/W2165589448","https://openalex.org/W2293401412","https://openalex.org/W3144926571","https://openalex.org/W6631338322","https://openalex.org/W6684367646","https://openalex.org/W6697076339"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W2536059291","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2100380429"],"abstract_inverted_index":{"We":[0,32,54,80,100],"investigate":[1],"the":[2,10,44,57,62,86,91,102,105,122,125,151,157],"use":[3,123],"of":[4,9,18,22,43,49,65,76,104,124,156],"local,":[5],"frame-dependent":[6,127],"reliability":[7,59],"indicators":[8,36,60],"audio":[11,117],"and":[12,95],"visual":[13],"modalities,":[14],"as":[15,41,72],"a":[16,66,73,109,132],"means":[17],"estimating":[19],"stream":[20,63,128,141],"exponents":[21,64,129],"multi-stream":[23],"hidden":[24,69],"Markov":[25,70],"models":[26],"for":[27],"audio-visual":[28,111],"automatic":[29],"speech":[30,112],"recognition.":[31],"consider":[33],"two":[34,82],"such":[35],"at":[37],"each":[38],"modality,":[39],"defined":[40],"functions":[42],"speech-class":[45],"conditional":[46,93],"observation":[47],"probabilities":[48],"appropriate":[50],"audio-or":[51],"visual-only":[52],"classifiers.":[53],"subsequently":[55],"map":[56],"four":[58],"into":[61],"state-synchronous,":[67],"two-stream":[68],"model,":[71],"sigmoid":[74,87],"function":[75],"their":[77],"linear":[78],"combination.":[79],"propose":[81],"algorithms":[83],"to":[84],"estimate":[85],"weights,":[88],"based":[89],"on":[90,108],"maximum":[92],"likelihood":[94],"minimum":[96],"classification":[97],"error":[98,136],"criteria.":[99],"demonstrate":[101],"superiority":[103],"proposed":[106],"approach":[107],"connected-digit":[110],"recognition":[113],"task,":[114],"under":[115],"varying":[116],"channel":[118],"noise":[119,159],"conditions.":[120],"Indeed,":[121],"estimated,":[126],"results":[130],"in":[131],"significantly":[133],"smaller":[134],"word":[135],"rate":[137],"than":[138],"using":[139],"global":[140],"exponents.":[142],"In":[143],"addition,":[144],"it":[145],"outperforms":[146],"utterance-level":[147],"exponents,":[148],"even":[149],"though":[150],"latter":[152],"utilize":[153],"a-priori":[154],"knowledge":[155],"utterance":[158],"level.":[160]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}