{"id":"https://openalex.org/W3160681319","doi":"https://doi.org/10.1109/icassp39728.2021.9414160","title":"A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection","display_name":"A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160681319","doi":"https://doi.org/10.1109/icassp39728.2021.9414160","mag":"3160681319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":1.2189,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78498986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6863","last_page":"6867"},"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":0.9991999864578247,"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":0.8097103834152222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7406021952629089},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5645604133605957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5503416061401367},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5150091648101807},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48727595806121826},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4716688096523285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42713862657546997},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4160385727882385},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4097590446472168},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32720711827278137},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10396572947502136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097103834152222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7406021952629089},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5645604133605957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5503416061401367},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5150091648101807},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48727595806121826},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4716688096523285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42713862657546997},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4160385727882385},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4097590446472168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32720711827278137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10396572947502136},{"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},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","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/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2963122170","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3016176723","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6754420807"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Audio-visual":[0],"automatic":[1],"speech":[2],"recognition":[3],"is":[4,107],"a":[5,29,54,81,176,183],"promising":[6],"approach":[7],"to":[8,64],"robust":[9],"ASR":[10],"under":[11,163,187],"noisy":[12],"conditions.":[13],"However,":[14],"up":[15],"until":[16],"recently":[17],"it":[18],"had":[19],"been":[20],"traditionally":[21],"studied":[22],"in":[23],"isolation":[24],"assuming":[25],"the":[26,34,38,66,75,90,94,97,100,115,125,128,148,151],"video":[27],"of":[28,138,150,193],"single":[30],"speaking":[31,101],"face":[32,102,195],"matches":[33],"audio,":[35],"and":[36,99,123,191],"selecting":[37],"active":[39,156],"speaker":[40,76,157],"at":[41,111,171],"inference":[42],"time":[43],"when":[44],"multiple":[45],"people":[46],"are":[47],"on":[48,154],"screen":[49],"was":[50,88],"put":[51],"aside":[52],"as":[53,142,173,175],"separate":[55],"problem.":[56],"As":[57],"an":[58,71,155,167],"alternative,":[59],"recent":[60],"work":[61,117],"has":[62],"proposed":[63],"address":[65],"two":[67,129],"problems":[68],"simultaneously":[69],"with":[70],"attention":[72,91,152],"mechanism,":[73],"baking":[74],"selection":[77,158],"problem":[78],"directly":[79],"into":[80],"fully":[82],"differentiable":[83],"model.":[84],"One":[85],"interesting":[86],"finding":[87],"that":[89,166,181],"indirectly":[92],"learns":[93],"association":[95],"between":[96,127],"audio":[98],"even":[103],"though":[104],"this":[105,121],"correspondence":[106],"never":[108],"explicitly":[109],"provided":[110],"training":[112,143],"time.":[113],"In":[114],"present":[116],"we":[118,145,161],"further":[119],"investigate":[120],"connection":[122],"examine":[124],"interplay":[126],"problems.":[130],"With":[131],"experiments":[132],"involving":[133],"over":[134],"50":[135],"thousand":[136],"hours":[137],"public":[139],"YouTube":[140],"videos":[141],"data,":[144],"first":[146],"evaluate":[147],"accuracy":[149],"layer":[153],"task.":[159],"Secondly,":[160],"show":[162],"closer":[164],"scrutiny":[165],"end-to-end":[168],"model":[169],"performs":[170],"least":[172],"well":[174],"considerably":[177],"larger":[178],"two-step":[179],"system":[180],"utilizes":[182],"hard":[184],"decision":[185],"boundary":[186],"various":[188],"noise":[189],"conditions":[190],"number":[192],"parallel":[194],"tracks.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}