{"id":"https://openalex.org/W4224923231","doi":"https://doi.org/10.1109/icassp43922.2022.9746036","title":"Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","display_name":"Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224923231","doi":"https://doi.org/10.1109/icassp43922.2022.9746036"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746036","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5048852285","display_name":"Otavio Braga","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Otavio Braga","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048852285"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.1032,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78988942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6047","last_page":"6051"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.8409281969070435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7829276323318481},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6798356175422668},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6289385557174683},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5647343397140503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4937320649623871},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4682261645793915},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45276299118995667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3444223403930664},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33614909648895264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409281969070435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7829276323318481},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6798356175422668},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6289385557174683},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5647343397140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4937320649623871},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4682261645793915},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45276299118995667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3444223403930664},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33614909648895264},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746036","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1614862348","https://openalex.org/W1828163288","https://openalex.org/W1974387177","https://openalex.org/W2029199293","https://openalex.org/W2033256038","https://openalex.org/W2096391593","https://openalex.org/W2112796928","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2167159094","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2950864153","https://openalex.org/W2963155035","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3016176723","https://openalex.org/W3160681319","https://openalex.org/W3203942572","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6749954789","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6770205713"],"related_works":["https://openalex.org/W2098693229","https://openalex.org/W2384651879","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049"],"abstract_inverted_index":{"Under":[0],"noisy":[1],"conditions,":[2],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"can":[7,66,112],"greatly":[8],"benefit":[9],"from":[10,17],"the":[11,21,53,58,77,82,86,122,129,139,145],"addition":[12],"of":[13,20,52,81,88],"visual":[14],"signals":[15],"coming":[16],"a":[18,35,108,117],"video":[19,79],"speaker\u2019s":[22],"face.":[23],"However,":[24],"when":[25,142],"multiple":[26],"candidate":[27],"speakers":[28],"are":[29],"visible":[30,54],"this":[31,99],"traditionally":[32],"requires":[33],"solving":[34],"separate":[36],"problem,":[37],"namely":[38],"active":[39,93,102],"speaker":[40,94,103],"detection":[41,104],"(ASD),":[42],"which":[43,51],"entails":[44],"selecting":[45],"at":[46,85],"each":[47],"moment":[48],"in":[49,101],"time":[50],"faces":[55],"corresponds":[56],"to":[57,144],"audio.":[59],"Recent":[60],"work":[61,97],"has":[62],"shown":[63],"that":[64,111],"we":[65,127],"solve":[67],"both":[68],"problems":[69],"simultaneously":[70,137],"by":[71,106,133],"employing":[72],"an":[73],"attention":[74],"mechanism":[75],"over":[76],"competing":[78],"tracks":[80],"speakers\u2019":[83],"faces,":[84],"cost":[87],"sacrificing":[89],"some":[90],"accuracy":[91,105,132],"on":[92],"detection.":[95],"This":[96],"closes":[98],"gap":[100],"presenting":[107],"single":[109],"model":[110],"be":[113],"jointly":[114],"trained":[115,148],"with":[116],"multi-task":[118],"loss.":[119],"By":[120],"combining":[121],"two":[123],"tasks":[124],"during":[125],"training":[126],"reduce":[128],"ASD":[130],"classification":[131],"approximately":[134],"25%,":[135],"while":[136],"improving":[138],"ASR":[140],"performance":[141],"compared":[143],"multi-person":[146],"baseline":[147],"exclusively":[149],"for":[150],"ASR.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}