{"id":"https://openalex.org/W4297841468","doi":"https://doi.org/10.21437/interspeech.2022-10866","title":"End-to-End multi-talker audio-visual ASR using an active speaker attention module","display_name":"End-to-End multi-talker audio-visual ASR using an active speaker attention module","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841468","doi":"https://doi.org/10.21437/interspeech.2022-10866"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10866","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10866","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081533291","display_name":"Richard Rose","orcid":"https://orcid.org/0000-0002-6603-1067"},"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":"Richard Rose","raw_affiliation_strings":["Google Inc., New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","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., New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2828","last_page":"2832"},"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":0.9983000159263611,"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":0.9980000257492065,"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":0.7784420251846313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.626600444316864},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42433232069015503},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17638534307479858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784420251846313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.626600444316864},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42433232069015503},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17638534307479858}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10866","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10866","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":26,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2033256038","https://openalex.org/W2144763279","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2508092598","https://openalex.org/W2890952074","https://openalex.org/W2963155035","https://openalex.org/W2963785710","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3016010032","https://openalex.org/W3016098309","https://openalex.org/W3016232124","https://openalex.org/W3109079702","https://openalex.org/W3143843080","https://openalex.org/W3187990717","https://openalex.org/W3196777808","https://openalex.org/W3196861523","https://openalex.org/W3200955206","https://openalex.org/W4224920409","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"This":[0],"paper":[1,96],"presents":[2],"a":[3,73,81],"new":[4],"approach":[5],"for":[6],"end-to-end":[7,76],"audio-visual":[8,84,110],"multi-talker":[9,51,111],"speech":[10,86],"recognition.The":[11],"approach,":[12],"referred":[13],"to":[14,32,36,66,105],"here":[15],"as":[16,72],"the":[17,28,44,63,67,95,98],"visual":[18],"context":[19],"attention":[20],"model":[21,77,100],"(VCAM),":[22],"is":[23,70,92],"important":[24],"because":[25],"it":[26],"uses":[27],"available":[29],"video":[30],"information":[31],"assign":[33,62],"decoded":[34],"text":[35],"one":[37],"of":[38],"multiple":[39,57],"visible":[40],"faces.This":[41],"essentially":[42],"resolves":[43],"label":[45,58,64],"ambiguity":[46],"issue":[47],"associated":[48],"with":[49,103],"most":[50],"modeling":[52],"approaches":[53],"which":[54],"can":[55],"decode":[56],"strings":[59,65],"but":[60],"cannot":[61],"correct":[68],"speakers.This":[69],"implemented":[71],"transformer-transducer":[74],"based":[75],"and":[78,109],"evaluated":[79],"using":[80],"two":[82],"speaker":[83],"overlapping":[85],"dataset":[87],"created":[88],"from":[89],"YouTube":[90],"videos.It":[91],"shown":[93],"in":[94],"that":[97],"VCAM":[99],"improves":[101],"performance":[102],"respect":[104],"previously":[106],"reported":[107],"audio-only":[108],"ASR":[112],"systems.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}