{"id":"https://openalex.org/W2957946919","doi":"https://doi.org/10.21437/interspeech.2019-1943","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","display_name":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2957946919","doi":"https://doi.org/10.21437/interspeech.2019-1943","mag":"2957946919"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1943","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.05337","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072051996","display_name":"Laurent El Shafey","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":"Laurent El Shafey","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010878109","display_name":"Hagen Soltau","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":"Hagen Soltau","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","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":"Izhak Shafran","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072051996"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.1573,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84230686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"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/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"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":0.9958000183105469,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.786806583404541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7698315382003784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7656701803207397},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6200432777404785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5784193277359009},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5654259920120239},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5458579063415527},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5213302969932556},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48457038402557373},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46191003918647766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3753041625022888},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36362549662590027},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09145194292068481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07168859243392944}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.786806583404541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698315382003784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7656701803207397},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6200432777404785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5784193277359009},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5654259920120239},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5458579063415527},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5213302969932556},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48457038402557373},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46191003918647766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3753041625022888},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36362549662590027},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09145194292068481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07168859243392944},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1943","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.05337","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05337","pdf_url":"https://arxiv.org/pdf/1907.05337","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2957946919","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.05337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.05337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.05337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.05337","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05337","pdf_url":"https://arxiv.org/pdf/1907.05337","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2957946919.pdf","grobid_xml":"https://content.openalex.org/works/W2957946919.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W309335912","https://openalex.org/W1517386993","https://openalex.org/W1828163288","https://openalex.org/W1965819578","https://openalex.org/W2064675550","https://openalex.org/W2081074144","https://openalex.org/W2114925438","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2166980079","https://openalex.org/W2173629880","https://openalex.org/W2405472765","https://openalex.org/W2513345070","https://openalex.org/W2545177271","https://openalex.org/W2606722458","https://openalex.org/W2638067502","https://openalex.org/W2786018489","https://openalex.org/W2786076697","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2901837390","https://openalex.org/W2911544293","https://openalex.org/W2950628382","https://openalex.org/W2963227667","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2973127116","https://openalex.org/W3025834604","https://openalex.org/W2902864383","https://openalex.org/W3114645670","https://openalex.org/W2945165156","https://openalex.org/W3006399655","https://openalex.org/W3034461631","https://openalex.org/W2899351468","https://openalex.org/W3156762052","https://openalex.org/W2951130829","https://openalex.org/W1974971289","https://openalex.org/W2912937645","https://openalex.org/W2890964092","https://openalex.org/W1494198834","https://openalex.org/W2607725416","https://openalex.org/W2293858598","https://openalex.org/W3003903817","https://openalex.org/W2165340520","https://openalex.org/W2091802891","https://openalex.org/W2920796740"],"abstract_inverted_index":{"Speech":[0],"applications":[1],"dealing":[2],"with":[3,55],"conversations":[4,154],"require":[5],"not":[6,70],"only":[7,137],"recognizing":[8],"the":[9,30,60,66,102,143],"spoken":[10],"words,":[11],"but":[12],"also":[13],"determining":[14],"who":[15],"spoke":[16],"when.":[17],"The":[18,49],"task":[19],"of":[20,32,145,152],"assigning":[21],"words":[22],"to":[23,72,92,100,126,132,160,174],"speakers":[24],"is":[25,79],"typically":[26],"addressed":[27],"by":[28,87,105],"merging":[29],"outputs":[31],"two":[33,50,103],"separate":[34],"systems,":[35,135],"namely,":[36],"an":[37,82],"automatic":[38],"speech":[39],"recognition":[40],"(ASR)":[41],"system":[42,111],"and":[43,68,76,109,123,157],"a":[44,97,106,113,149,161],"speaker":[45,128],"diarization":[46,169],"(SD)":[47],"system.":[48],"systems":[51,62],"are":[52,69],"trained":[53],"independently":[54],"different":[56],"objective":[57],"functions.":[58],"Often":[59],"SD":[61,110,134],"operate":[63],"directly":[64],"on":[65,148],"acoustics":[67],"constrained":[71],"respect":[73],"word":[74],"boundaries":[75],"this":[77],"deficiency":[78],"overcome":[80],"in":[81,90],"ad":[83],"hoc":[84],"manner.":[85],"Motivated":[86],"recent":[88],"advances":[89],"sequence":[91,93],"learning,":[94],"we":[95],"propose":[96],"novel":[98],"approach":[99,119,147,166],"tackle":[101],"tasks":[104],"joint":[107],"ASR":[108],"using":[112],"recurrent":[114],"neural":[115],"network":[116],"transducer.":[117],"Our":[118],"utilizes":[120],"both":[121],"linguistic":[122],"acoustic":[124,139],"cues":[125],"infer":[127],"roles,":[129],"as":[130],"opposed":[131],"typical":[133],"which":[136],"use":[138],"cues.":[140],"We":[141],"evaluated":[142],"performance":[144],"our":[146,165],"large":[150],"corpus":[151],"medical":[153],"between":[155],"physicians":[156],"patients.":[158],"Compared":[159],"competitive":[162],"conventional":[163],"baseline,":[164],"improves":[167],"word-level":[168],"error":[170],"rate":[171],"from":[172],"15.8%":[173],"2.2%.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}