{"id":"https://openalex.org/W2972921407","doi":"https://doi.org/10.21437/interspeech.2019-1769","title":"Disentangling Style Factors from Speaker Representations","display_name":"Disentangling Style Factors from Speaker Representations","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972921407","doi":"https://doi.org/10.21437/interspeech.2019-1769","mag":"2972921407"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1769","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1769","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/20.500.11820/78d71614-2321-4278-9dd0-36994c8e203c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040626187","display_name":"Jennifer Williams","orcid":"https://orcid.org/0000-0003-1410-0427"},"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":true,"raw_author_name":"Jennifer Williams","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040626187"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3945","last_page":"3949"},"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/T10181","display_name":"Natural Language Processing Techniques","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":0.9968000054359436,"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/style","display_name":"Style (visual arts)","score":0.7570450901985168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338700652122498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4503003656864166},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4114784896373749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3979523777961731},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38858562707901},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.10645970702171326}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7570450901985168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338700652122498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4503003656864166},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4114784896373749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3979523777961731},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38858562707901},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.10645970702171326},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-1769","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1769","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:eprints.soton.ac.uk:467453","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/467453/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/78d71614-2321-4278-9dd0-36994c8e203c","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/78d71614-2321-4278-9dd0-36994c8e203c","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Williams, J & King, S 2019, Disentangling style factors from speaker representations. in Proceedings Interspeech 2019. vol. 2019-September, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 3945-3949, 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1769","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/78d71614-2321-4278-9dd0-36994c8e203c","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2019/williams19c_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":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/78d71614-2321-4278-9dd0-36994c8e203c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/78d71614-2321-4278-9dd0-36994c8e203c","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Williams, J & King, S 2019, Disentangling style factors from speaker representations. in Proceedings Interspeech 2019. vol. 2019-September, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 3945-3949, 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1769","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/78d71614-2321-4278-9dd0-36994c8e203c","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/78d71614-2321-4278-9dd0-36994c8e203c","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Williams, J & King, S 2019, Disentangling style factors from speaker representations. in Proceedings Interspeech 2019. vol. 2019-September, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 3945-3949, 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1769","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1547742344","https://openalex.org/W1548765444","https://openalex.org/W1572063013","https://openalex.org/W2004915807","https://openalex.org/W2121812409","https://openalex.org/W2146334809","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2395750323","https://openalex.org/W2404143005","https://openalex.org/W2405404369","https://openalex.org/W2726515241","https://openalex.org/W2747664154","https://openalex.org/W2748488820","https://openalex.org/W2766406951","https://openalex.org/W2794490148","https://openalex.org/W2794506738","https://openalex.org/W2807305309","https://openalex.org/W2808631503","https://openalex.org/W2885800352","https://openalex.org/W2886300652","https://openalex.org/W2888976508","https://openalex.org/W2890964092","https://openalex.org/W2901611695","https://openalex.org/W2953384591","https://openalex.org/W2962691331","https://openalex.org/W2963418523"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"Our":[0,147],"goal":[1],"is":[2,70,82,145],"to":[3,124,161,170,174],"separate":[4,116,125],"out":[5],"speaking":[6,38],"style":[7,39,163,176],"from":[8,138],"speaker":[9,34,79,131,182],"identity":[10],"in":[11,65,178],"utterance-level":[12],"representations":[13],"of":[14,88,94,181],"speech":[15],"such":[16],"as":[17,99,122,162],"i-vectors":[18,26],"and":[19,27,80,101,140],"x-vectors.":[20],"We":[21,109],"first":[22],"show":[23],"that":[24,91,102,150],"both":[25],"x-vectors":[28],"contain":[29,155],"information":[30,77,144,172],"not":[31],"only":[32],"about":[33,37,78],"but":[35],"also":[36],"(for":[40,46],"one":[41,93],"data":[42,48],"set)":[43],"or":[44],"emotion":[45],"another":[47],"set),":[49],"even":[50],"when":[51],"projected":[52],"into":[53,72],"a":[54],"low-dimensional":[55],"space.":[56],"To":[57],"disentangle":[58],"these":[59],"factors,":[60],"we":[61,159,166],"use":[62,87,171],"an":[63],"autoencoder":[64],"which":[66,158],"the":[67,86,95,107,113,117,142,179],"latent":[68,97,114],"space":[69],"split":[71],"two":[73,96],"subspaces.":[74],"The":[75],"entangled":[76],"style/emotion":[81,126],"pushed":[83],"apart":[84],"by":[85,119],"auxiliary":[89],"classifiers":[90],"take":[92],"subspaces":[98,115],"input":[100,123],"are":[103,136],"jointly":[104],"learned":[105],"with":[106],"autoencoder.":[108],"evaluate":[110],"how":[111],"well":[112],"factors":[118,177],"using":[120],"them":[121],"classification":[127],"tasks.":[128],"In":[129],"traditional":[130],"identification":[132],"tasks,":[133],"speaker-invariant":[134],"characteristics":[135],"factorized":[137],"channel":[139,143,153],"then":[141],"ignored.":[146],"results":[148],"suggest":[149],"this":[151],"so-called":[152],"may":[154],"exploitable":[156],"information,":[157],"refer":[160],"factors.":[164],"Finally,":[165],"propose":[167],"future":[168],"work":[169],"theory":[173],"formalize":[175],"context":[180],"identity.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}