{"id":"https://openalex.org/W4391021406","doi":"https://doi.org/10.1109/asru57964.2023.10389736","title":"Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers","display_name":"Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021406","doi":"https://doi.org/10.1109/asru57964.2023.10389736"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5003272316","display_name":"Guru Prakash Arumugam","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":"Guru Prakash Arumugam","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A","Google LLC, Mountain View, CA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","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":"Shuo-Yiin Chang","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A","Google LLC, Mountain View, CA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745454","display_name":"Tara N. Sainath Rohit Prabhavalkar","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":"Tara N. Sainath Rohit Prabhavalkar","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A","Google LLC, Mountain View, CA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"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":"Quan Wang","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A","Google LLC, Mountain View, CA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057214137","display_name":"Shaan Bijwadia","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":"Shaan Bijwadia","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A","Google LLC, Mountain View, CA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, U.S.A","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/primary","display_name":"Primary (astronomy)","score":0.7913141250610352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7428607940673828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7099628448486328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40289148688316345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3267861008644104}],"concepts":[{"id":"https://openalex.org/C2777977315","wikidata":"https://www.wikidata.org/wiki/Q7243056","display_name":"Primary (astronomy)","level":2,"score":0.7913141250610352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7428607940673828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099628448486328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40289148688316345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3267861008644104},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2221409856","https://openalex.org/W2612434969","https://openalex.org/W2617258110","https://openalex.org/W2886025712","https://openalex.org/W2891367150","https://openalex.org/W2928941594","https://openalex.org/W2935756939","https://openalex.org/W2962745521","https://openalex.org/W2962788625","https://openalex.org/W2963122170","https://openalex.org/W2963414781","https://openalex.org/W2963470929","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3013139777","https://openalex.org/W3015194534","https://openalex.org/W3044278286","https://openalex.org/W3097777922","https://openalex.org/W3139918052","https://openalex.org/W3143843080","https://openalex.org/W3149629662","https://openalex.org/W3163203022","https://openalex.org/W3163907627","https://openalex.org/W3197533300","https://openalex.org/W3197898596","https://openalex.org/W3197976839","https://openalex.org/W3203417382","https://openalex.org/W3204696009","https://openalex.org/W3212886388","https://openalex.org/W4225307083","https://openalex.org/W4225529283","https://openalex.org/W4225873749","https://openalex.org/W4286908472","https://openalex.org/W4319862683","https://openalex.org/W4372259861","https://openalex.org/W6675365184","https://openalex.org/W6737575990","https://openalex.org/W6754496211","https://openalex.org/W6760633627","https://openalex.org/W6780404847","https://openalex.org/W6791904447","https://openalex.org/W6840509714"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2949989742","https://openalex.org/W2168220598","https://openalex.org/W3204019825"],"abstract_inverted_index":{"ASR":[0,41],"models":[1],"often":[2],"suffer":[3],"from":[4,87],"a":[5,20,34,96],"long-form":[6,66,131],"deletion":[7,67,132],"problem":[8],"where":[9],"the":[10,24,31,40,49,56,63,77,107,111,124,130],"model":[11,50,78,101,136],"predicts":[12],"sequential":[13],"blanks":[14],"instead":[15],"of":[16,26,33,62,104],"words":[17],"when":[18,76],"transcribing":[19],"lengthy":[21],"audio":[22,108],"(in":[23],"order":[25],"minutes":[27],"or":[28,36,147],"hours).":[29],"From":[30],"perspective":[32],"user":[35],"downstream":[37],"system":[38],"consuming":[39],"results,":[42],"this":[43,92],"behavior":[44],"can":[45,73],"be":[46],"perceived":[47],"as":[48,118],"\u201cbeing":[51],"stuck\u201d,":[52],"and":[53,83,120,127],"potentially":[54],"make":[55],"product":[57],"hard":[58],"to":[59,99],"use.":[60],"One":[61],"culprits":[64],"for":[65],"is":[68,79],"training-test":[69],"data":[70,85,142],"mismatch,":[71],"which":[72,122],"happen":[74],"even":[75],"trained":[80],"on":[81],"diverse":[82],"large-scale":[84],"collected":[86],"multiple":[88],"application":[89,125],"domains.":[90],"In":[91],"work,":[93],"we":[94],"introduce":[95],"novel":[97],"technique":[98],"simultaneously":[100],"different":[102],"groups":[103],"speakers":[105],"in":[106],"along":[109],"with":[110],"standard":[112],"transcript":[113],"tokens.":[114],"Speakers":[115],"are":[116],"grouped":[117],"primary":[119],"non-primary,":[121],"connects":[123],"domains":[126],"significantly":[128],"alleviates":[129],"problem.":[133],"This":[134],"improved":[135],"neither":[137],"needs":[138],"any":[139],"additional":[140,145],"training":[141,146],"nor":[143],"incurs":[144],"inference":[148],"cost.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}