{"id":"https://openalex.org/W4296069358","doi":"https://doi.org/10.21437/interspeech.2022-10643","title":"Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations","display_name":"Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069358","doi":"https://doi.org/10.21437/interspeech.2022-10643"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10643","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10643","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":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/293601883/Investigating_the_contribution_LUU_DOA13062022_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020396429","display_name":"Chau Luu","orcid":null},"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":"Chau Luu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101955379","display_name":"Peter Bell","orcid":"https://orcid.org/0009-0003-6824-4343"},"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":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.993399977684021,"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-recognition","display_name":"Speaker recognition","score":0.786257803440094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.714409589767456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.700904369354248},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6279892921447754},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.44989272952079773},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.44867607951164246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3534565567970276}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.786257803440094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714409589767456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.700904369354248},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6279892921447754},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.44989272952079773},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.44867607951164246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3534565567970276}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10643","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10643","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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/96df4d54-1eb6-40f2-991b-32ec01699f7e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/96df4d54-1eb6-40f2-991b-32ec01699f7e","pdf_url":"https://www.research.ed.ac.uk/files/293601883/Investigating_the_contribution_LUU_DOA13062022_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luu, C, Renals, S & Bell, P 2022, Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations. in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022. pp. 610-614, Interspeech 2022, Incheon, Korea, Republic of, 18/09/22. https://doi.org/10.21437/Interspeech.2022-10643","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/96df4d54-1eb6-40f2-991b-32ec01699f7e","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2022/luu22_interspeech.html","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/96df4d54-1eb6-40f2-991b-32ec01699f7e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/96df4d54-1eb6-40f2-991b-32ec01699f7e","pdf_url":"https://www.research.ed.ac.uk/files/293601883/Investigating_the_contribution_LUU_DOA13062022_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luu, C, Renals, S & Bell, P 2022, Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations. in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022. pp. 610-614, Interspeech 2022, Incheon, Korea, Republic of, 18/09/22. https://doi.org/10.21437/Interspeech.2022-10643","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296069358.pdf","grobid_xml":"https://content.openalex.org/works/W4296069358.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W1971017968","https://openalex.org/W2150769028","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2510867321","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2902476877","https://openalex.org/W2950662112","https://openalex.org/W2972921407","https://openalex.org/W2998115938","https://openalex.org/W3008391559","https://openalex.org/W3015707499","https://openalex.org/W3016090709","https://openalex.org/W3026687426","https://openalex.org/W3098439673","https://openalex.org/W3184252821","https://openalex.org/W3198024420","https://openalex.org/W3203542076","https://openalex.org/W3207051247"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W4401661962","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Deep":[0],"speaker":[1,38,56,84,146,163],"embeddings":[2],"have":[3],"been":[4],"shown":[5],"to":[6,14,23,64,77,92,172],"encode":[7,93],"a":[8,15,54,155,173],"wide":[9],"variety":[10],"of":[11,19,27,37,42,53,72,82,158],"attributes":[12,29,123],"relating":[13],"speaker.":[16],"The":[17],"aim":[18],"this":[20,106,115,143],"work":[21,68],"is":[22,47,60,117,154],"separate":[24],"out":[25,121],"some":[26],"these":[28,35],"in":[30,119,124,160],"the":[31,43,50,83,99,125,135,161],"embedding":[32,44,57,85,126,164],"space,":[33,127,165],"disentangling":[34,129],"sources":[36],"variation":[39],"into":[40],"subsets":[41,81],"dimensions.":[45,86],"This":[46,67],"achieved":[48],"modifying":[49],"training":[51],"procedure":[52],"typical":[55],"network,":[58],"which":[59],"typically":[61],"only":[62],"trained":[63],"classify":[65],"speakers.":[66],"instead":[69],"adds":[70],"pairs":[71],"attribute":[73],"specific":[74,88],"task":[75],"heads":[76],"operate":[78],"on":[79],"complementary":[80],"While":[87],"dimensions":[89,101],"are":[90,102],"encouraged":[91],"an":[94,109],"attribute,":[95],"for":[96,104],"example":[97],"gender,":[98,130],"other":[100],"penalized":[103],"containing":[105],"information":[107,144],"using":[108],"adversarial":[110],"loss.":[111],"We":[112],"show":[113],"that":[114,152],"method":[116],"effective":[118],"factorizing":[120],"multiple":[122],"successfully":[128],"nationality":[131,167],"and":[132,148,168],"age.":[133],"Using":[134],"disentangled":[136],"representations,":[137],"we":[138],"investigate":[139],"how":[140],"much":[141],"removing":[142],"impacts":[145],"verification":[147],"diarization":[149],"performance,":[150],"showing":[151],"gender":[153],"significant":[156],"source":[157],"separation":[159],"deep":[162],"with":[166],"age":[169],"also":[170],"contributing":[171],"lesser":[174],"degree.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}