{"id":"https://openalex.org/W1985158632","doi":"https://doi.org/10.1109/asru.2009.5373530","title":"Audio-visual automatic speech recognition and related bimodal speech technologies: A review of the state-of-the-art and open problems","display_name":"Audio-visual automatic speech recognition and related bimodal speech technologies: A review of the state-of-the-art and open problems","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W1985158632","doi":"https://doi.org/10.1109/asru.2009.5373530","mag":"1985158632"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},"type":"review","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/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, National Centre for Scientific Research \"Demokritos\", Athens, Greece","Institute of Informatics and Telecommunications, National Centre for Scientific Research \u00bfDemokritos\u00bf, GR-15310 Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, National Centre for Scientific Research \"Demokritos\", Athens, Greece","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"Institute of Informatics and Telecommunications, National Centre for Scientific Research \u00bfDemokritos\u00bf, GR-15310 Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024184433"],"corresponding_institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"],"apc_list":null,"apc_paid":null,"fwci":0.3525,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.53517792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9697999954223633,"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":0.8166224956512451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7158094644546509},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6108046770095825},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5483076572418213},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5453812479972839},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5114649534225464},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4776381552219391},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47511324286460876},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45185697078704834},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4516651928424835},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41718894243240356},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4109208583831787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32444190979003906},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24446481466293335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166224956512451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7158094644546509},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6108046770095825},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5483076572418213},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5453812479972839},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5114649534225464},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4776381552219391},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47511324286460876},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45185697078704834},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4516651928424835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41718894243240356},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4109208583831787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32444190979003906},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24446481466293335},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W134179020","https://openalex.org/W1541790149","https://openalex.org/W2184127972","https://openalex.org/W4312668661","https://openalex.org/W2355899496","https://openalex.org/W2525874696","https://openalex.org/W2131711534","https://openalex.org/W2008120082","https://openalex.org/W642007152","https://openalex.org/W2218471654"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"The":[4,35],"presentation":[5],"will":[6],"provide":[7],"an":[8],"overview":[9],"of":[10,21,30,39,50,70,121],"the":[11,16,19,28,42,48,57,71,89,127,133,137,144],"main":[12],"research":[13,44],"achievements":[14],"and":[15,81,99,155],"state-of-the-art":[17],"in":[18,27,41,94,107,143],"area":[20,29],"audiovisual":[22],"speech":[23,33,43,78,124,129,150],"processing,":[24],"mainly":[25],"focusing":[26],"audio-visual":[31,82,90,100,123],"automatic":[32],"recognition.":[34],"topic":[36],"has":[37,136],"been":[38],"interest":[40],"community":[45],"due":[46],"to":[47,53,88,139],"potential":[49,138],"increased":[51],"robustness":[52],"acoustic":[54],"noise":[55],"that":[56,65,85],"visual":[58,77,134],"modality":[59,135],"holds.":[60],"Nevertheless,":[61],"significant":[62],"challenges":[63,114],"remain":[64,86],"have":[66],"hindered":[67],"practical":[68],"applications":[69],"technology":[72],"most":[73],"notably":[74],"difficulties":[75],"with":[76],"information":[79],"extraction":[80],"fusion":[83],"algorithms":[84],"robust":[87],"environment":[91],"variability":[92],"inherent":[93,142],"practical,":[95],"unconstrained":[96],"interaction":[97,106],"scenarios":[98],"data":[101],"sources,":[102],"for":[103,148],"example":[104],"multiparty":[105],"smart":[108],"spaces,":[109],"broadcast":[110],"news,":[111],"etc.":[112],"These":[113],"are":[115],"also":[116],"shared":[117],"across":[118],"a":[119],"number":[120],"interesting":[122],"technologies":[125],"beyond":[126],"core":[128],"recognition":[130],"problem,":[131],"where":[132],"resolve":[140],"ambiguity":[141],"audio":[145],"signal":[146],"alone;":[147],"example,":[149],"activity":[151],"detection,":[152],"speaker":[153],"diarization,":[154],"source":[156],"separation.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}