{"id":"https://openalex.org/W3097182716","doi":"https://doi.org/10.21437/interspeech.2021-622","title":"Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization","display_name":"Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3097182716","doi":"https://doi.org/10.21437/interspeech.2021-622","mag":"3097182716"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-622","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020396429","display_name":"Chau Luu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chau Luu","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9965999722480774,"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":0.9948999881744385,"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":0.8810855150222778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250985145568848},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7050608992576599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6897578239440918},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6093452572822571},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5925945043563843},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5494663715362549},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4963091015815735},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4939749836921692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4636361002922058},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.45493704080581665},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41006308794021606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3751724660396576}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8810855150222778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250985145568848},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7050608992576599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6897578239440918},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6093452572822571},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5925945043563843},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5494663715362549},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4963091015815735},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4939749836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4636361002922058},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45493704080581665},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41006308794021606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3751724660396576},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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":5,"locations":[{"id":"doi:10.21437/interspeech.2021-622","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.14269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14269","pdf_url":"https://arxiv.org/pdf/2010.14269","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:3097182716","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14269","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":"pmh:oai:pure.ed.ac.uk:openaire/2d161123-7917-4c15-84ec-b9b9743239a2","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2d161123-7917-4c15-84ec-b9b9743239a2","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luu, C, Bell, P & Renals, S 2021, Leveraging Speaker Attribute Information Using Multi Task Learning for Speaker Verification and Diarization. in Proceedings of Interspeech 2021. International Speech Communication Association, pp. 491-495, Interspeech 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-622","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2010.14269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14269","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14269","pdf_url":"https://arxiv.org/pdf/2010.14269","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W161476681","https://openalex.org/W173856587","https://openalex.org/W1524333225","https://openalex.org/W1936725236","https://openalex.org/W1987847367","https://openalex.org/W2057827229","https://openalex.org/W2150769028","https://openalex.org/W2345474290","https://openalex.org/W2550928100","https://openalex.org/W2726515241","https://openalex.org/W2805709749","https://openalex.org/W2808631503","https://openalex.org/W2887499727","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2914746235","https://openalex.org/W2962898354","https://openalex.org/W2972921407","https://openalex.org/W2993724474","https://openalex.org/W3008391559","https://openalex.org/W3015707499","https://openalex.org/W3016090709","https://openalex.org/W3025125834","https://openalex.org/W3042609801","https://openalex.org/W3044308976"],"related_works":["https://openalex.org/W3198024420","https://openalex.org/W3015988545","https://openalex.org/W3015826515","https://openalex.org/W2901404901","https://openalex.org/W1591187112","https://openalex.org/W2787692317","https://openalex.org/W3015555484","https://openalex.org/W3131327410","https://openalex.org/W2938358845","https://openalex.org/W135211875","https://openalex.org/W3015923889","https://openalex.org/W2969867981","https://openalex.org/W3162184950","https://openalex.org/W3016234652","https://openalex.org/W2757927421","https://openalex.org/W3177220826","https://openalex.org/W2972595148","https://openalex.org/W2914064142","https://openalex.org/W2963449399","https://openalex.org/W2938265499"],"abstract_inverted_index":{"Deep":[0,46],"speaker":[1,10,13,47,54,131,151,175],"embeddings":[2,48,152],"have":[3],"become":[4],"the":[5,22,29,58,110,137,146,183,190],"leading":[6],"method":[7],"for":[8,92,105,153],"encoding":[9,28],"identity":[11,55],"in":[12,165,169],"recognition":[14],"tasks.":[15],"The":[16],"embedding":[17],"space":[18],"should":[19],"ideally":[20],"capture":[21],"variations":[23],"between":[24],"all":[25],"possible":[26],"speakers,":[27],"multiple":[30],"acoustic":[31,44],"aspects":[32],"that":[33,63,79,124],"make":[34],"up":[35],"a":[36,90,114,160],"speaker's":[37],"identity,":[38],"whilst":[39],"being":[40,193],"robust":[41],"to":[42,83,85,109,172],"non-speaker":[43],"variation.":[45],"are":[49,80],"normally":[50],"trained":[51],"discriminatively,":[52],"predicting":[53,65],"labels":[56,176,185],"on":[57],"training":[59,139],"data.":[60],"We":[61,88],"hypothesise":[62],"additionally":[64],"speaker-related":[66],"auxiliary":[67,96,184],"variables":[68],"--":[69,75],"such":[70],"as":[71],"age":[72],"and":[73,141,156,167,192],"nationality":[74],"may":[76],"yield":[77],"representations":[78],"better":[81],"able":[82],"generalise":[84],"unseen":[86],"speakers.":[87],"propose":[89],"framework":[91],"making":[93],"use":[94],"of":[95,117,130,148,163],"label":[97],"information,":[98],"even":[99],"when":[100],"it":[101],"is":[102,180],"only":[103],"available":[104],"speech":[106],"corpora":[107],"mismatched":[108],"target":[111],"application.":[112],"On":[113],"test":[115],"set":[116],"US":[118],"Supreme":[119],"Court":[120],"recordings,":[121],"we":[122,144],"show":[123],"by":[125],"leveraging":[126],"two":[127],"additional":[128],"forms":[129],"attribute":[132],"information":[133],"derived":[134],"respectively":[135],"from":[136,189],"matched":[138],"data,":[140],"VoxCeleb":[142],"corpus,":[143],"improve":[145],"performance":[147],"our":[149],"deep":[150],"both":[154],"verification":[155],"diarization":[157],"tasks,":[158],"achieving":[159],"relative":[161],"improvement":[162,179],"26.2%":[164],"DER":[166],"6.7%":[168],"EER":[170],"compared":[171],"baselines":[173],"using":[174],"only.":[177],"This":[178],"obtained":[181],"despite":[182],"having":[186],"been":[187],"scraped":[188],"web":[191],"potentially":[194],"noisy.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}