{"id":"https://openalex.org/W3016176723","doi":"https://doi.org/10.1109/icassp40776.2020.9053974","title":"End-to-End Multi-Person Audio/Visual Automatic Speech Recognition","display_name":"End-to-End Multi-Person Audio/Visual Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016176723","doi":"https://doi.org/10.1109/icassp40776.2020.9053974","mag":"3016176723"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":"middle","author":{"id":"https://openalex.org/A5108496023","display_name":"Takaki Makino","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":"Takaki Makino","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","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":"Hank Liao","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":4,"corresponding_author_ids":["https://openalex.org/A5048852285"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.8184,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85470704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6994","last_page":"6998"},"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":0.9986000061035156,"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":0.9968000054359436,"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":0.854934811592102},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7169176340103149},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6054860949516296},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.547142505645752},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5246636867523193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722945988178253},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4629443883895874},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4611826539039612},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4231877326965332},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37491855025291443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2234872579574585},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17053186893463135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.854934811592102},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7169176340103149},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6054860949516296},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.547142505645752},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5246636867523193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722945988178253},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4629443883895874},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4611826539039612},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4231877326965332},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37491855025291443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2234872579574585},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17053186893463135},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1614862348","https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W1974387177","https://openalex.org/W2096733369","https://openalex.org/W2112796928","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2949520286","https://openalex.org/W2950864153","https://openalex.org/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2964308564","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3099206234","https://openalex.org/W3209042722","https://openalex.org/W3210232381","https://openalex.org/W4288327876","https://openalex.org/W6637373629","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6735927292","https://openalex.org/W6749954789","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6764045775","https://openalex.org/W6803376173"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2125620709","https://openalex.org/W2110441383","https://openalex.org/W2045932760","https://openalex.org/W4233149903","https://openalex.org/W2326878701","https://openalex.org/W2098693229","https://openalex.org/W2384651879","https://openalex.org/W2354332708"],"abstract_inverted_index":{"Traditionally,":[0],"audio-visual":[1],"automatic":[2],"speech":[3],"recognition":[4],"has":[5],"been":[6],"studied":[7],"under":[8],"the":[9,12,16,20,23,47,55,66,122,130,152,158,172,181,186],"assumption":[10],"that":[11,86,125,151],"speaking":[13,173],"face":[14,21,43,92,106,114,132,160,174],"on":[15,36,73,100,111,138,143],"visual":[17,182],"signal":[18,183],"is":[19,87,126],"matching":[22],"audio.":[24],"However,":[25],"in":[26,94],"a":[27,80,95,112],"more":[28],"realistic":[29],"setting,":[30],"when":[31],"multiple":[32,69,91],"faces":[33],"are":[34,71],"potentially":[35],"screen":[37,74],"one":[38,61],"needs":[39],"to":[40,44,46,89,121,128,167],"decide":[41],"which":[42],"feed":[45],"A/V":[48,59,76,83,140],"ASR":[49,60,84,110,123],"system.":[50],"The":[51],"present":[52],"work":[53],"takes":[54],"recent":[56],"progress":[57],"of":[58,98,147,171,179,185],"step":[62],"further":[63],"and":[64,108],"considers":[65],"scenario":[67],"where":[68],"people":[70],"simultaneously":[72],"(multi-person":[75],"ASR).":[77],"We":[78],"propose":[79],"fully":[81],"differentiable":[82],"model":[85],"able":[88,127],"handle":[90],"tracks":[93,161],"video.":[96],"Instead":[97],"relying":[99],"two":[101],"separate":[102],"models":[103],"for":[104],"speaker":[105],"selection":[107,170],"audiovisual":[109],"single":[113],"track,":[115],"we":[116],"introduce":[117],"an":[118,139,168],"attention":[119],"layer":[120],"encoder":[124],"soft-select":[129],"appropriate":[131],"video":[133],"track.":[134],"Experiments":[135],"carried":[136],"out":[137],"system":[141],"trained":[142],"over":[144],"30k":[145],"hours":[146],"YouTube":[148],"videos":[149],"illustrate":[150],"proposed":[153],"approach":[154],"can":[155],"automatically":[156],"select":[157],"proper":[159],"with":[162],"minor":[163],"WER":[164],"degradation":[165],"compared":[166],"oracle":[169],"while":[175],"still":[176],"showing":[177],"benefits":[178],"employing":[180],"instead":[184],"audio":[187],"alone.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
