{"id":"https://openalex.org/W4235272953","doi":"https://doi.org/10.1109/icme.2003.1221384","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":"2003-01-01","ids":{"openalex":"https://openalex.org/W4235272953","doi":"https://doi.org/10.1109/icme.2003.1221384"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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":true,"raw_author_name":"A. Garg","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana, IL, USA"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"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, IL, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002107058"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.2928,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63172043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"III","last_page":"605"},"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":0.9976999759674072,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7124346494674683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.677215576171875},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5926322937011719},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4914354085922241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47591930627822876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47466304898262024},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4361543357372284},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.41330277919769287},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1255248486995697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124346494674683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.677215576171875},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5926322937011719},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4914354085922241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47591930627822876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47466304898262024},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4361543357372284},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.41330277919769287},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1255248486995697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1221384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"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/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/W4307784074","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"We":[0,32,55,81,101],"investigate":[1],"the":[2,10,44,58,63,87,92,103,106,123,151,157],"use":[3,124],"of":[4,9,18,22,43,49,66,77,105,125,156],"local,":[5],"frame-dependent":[6,127],"reliability":[7,60],"indicators":[8,36,61],"audio":[11,51,118],"and":[12,96],"visual":[13],"modalities,":[14],"as":[15,41,73],"a":[16,67,74,110,132],"means":[17],"estimating":[19],"stream":[20,64,128,141],"exponents":[21,65,129],"multi-stream":[23],"hidden":[24,70],"Markov":[25,71],"models":[26],"for":[27],"audio-visual":[28,112],"automatic":[29],"speech":[30,113],"recognition.":[31],"consider":[33],"two":[34,83],"such":[35],"at":[37],"each":[38],"modality,":[39],"defined":[40],"functions":[42],"speech-class":[45],"conditional":[46,94],"observation":[47],"probabilities":[48],"appropriate":[50],"or":[52],"visual-only":[53],"classifiers.":[54],"subsequently":[56],"map":[57],"four":[59],"into":[62],"state-synchronous,":[68],"two-stream":[69],"model,":[72],"sigmoid":[75,88],"function":[76],"their":[78],"linear":[79],"combination.":[80],"propose":[82],"algorithms":[84],"to":[85],"estimate":[86],"weights,":[89],"based":[90],"on":[91,109],"maximum":[93],"likelihood":[95],"minimum":[97],"classification":[98],"error":[99,136],"criteria.":[100],"demonstrate":[102],"superiority":[104],"proposed":[107],"approach":[108],"connected-digit":[111],"recognition":[114],"task,":[115],"under":[116],"varying":[117],"channel":[119],"noise":[120,159],"conditions.":[121],"Indeed,":[122],"estimated,":[126],"results":[130],"in":[131],"significantly":[133],"smaller":[134],"word":[135],"rare":[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":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
