{"id":"https://openalex.org/W3096791609","doi":"https://doi.org/10.21437/interspeech.2020-2567","title":"An Unsupervised Method to Select a Speaker Subset from Large Multi-Speaker Speech Synthesis Datasets","display_name":"An Unsupervised Method to Select a Speaker Subset from Large Multi-Speaker Speech Synthesis Datasets","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096791609","doi":"https://doi.org/10.21437/interspeech.2020-2567","mag":"3096791609"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/369969791/GallegosEtal2020AnUnsupervisedMethod.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035966487","display_name":"Pilar Oplustil Gallegos","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":"Pilar Oplustil Gallegos","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":"middle","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":false,"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":"middle","author":{"id":"https://openalex.org/A5026578899","display_name":"Joanna Rownicka","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":"Joanna Rownicka","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]}],"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":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1758","last_page":"1762"},"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":0.998199999332428,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7904317378997803},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7318528890609741},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6945396661758423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6871188879013062},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4557792842388153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858272433280945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904317378997803},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7318528890609741},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6945396661758423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6871188879013062},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4557792842388153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858272433280945}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f22287ce-6508-4603-869c-77664ac658da","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f22287ce-6508-4603-869c-77664ac658da","pdf_url":"https://www.research.ed.ac.uk/files/369969791/GallegosEtal2020AnUnsupervisedMethod.pdf","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.soton.ac.uk:467438","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/467438/","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:publications/f22287ce-6508-4603-869c-77664ac658da","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/f22287ce-6508-4603-869c-77664ac658da","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:publications/f22287ce-6508-4603-869c-77664ac658da","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f22287ce-6508-4603-869c-77664ac658da","pdf_url":"https://www.research.ed.ac.uk/files/369969791/GallegosEtal2020AnUnsupervisedMethod.pdf","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4437068315","display_name":"EPSRC Centre for Doctoral Training in Data Science","funder_award_id":"EP/L016427/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320331146","display_name":"Agencia Nacional de Investigaci\u00f3n y Desarrollo","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096791609.pdf","grobid_xml":"https://content.openalex.org/works/W3096791609.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1547848553","https://openalex.org/W2101234009","https://openalex.org/W2120847449","https://openalex.org/W2170980774","https://openalex.org/W2483256596","https://openalex.org/W2527515520","https://openalex.org/W2746419079","https://openalex.org/W2749074593","https://openalex.org/W2765860599","https://openalex.org/W2767052532","https://openalex.org/W2889414197","https://openalex.org/W2890964092","https://openalex.org/W2913512413","https://openalex.org/W2936802426","https://openalex.org/W2940703732","https://openalex.org/W2963542120","https://openalex.org/W2964243274","https://openalex.org/W2973143722","https://openalex.org/W3020176785","https://openalex.org/W3024752295"],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916","https://openalex.org/W2144470400","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Large":[0],"multi-speaker":[1],"datasets":[2],"for":[3],"TTS":[4],"typically":[5],"contain":[6],"diverse":[7],"speakers,":[8],"recording":[9],"conditions,":[10],"styles":[11],"and":[12],"quality":[13,46],"of":[14,39],"data.":[15],"Although":[16],"one":[17],"might":[18],"generally":[19],"presume":[20],"that":[21,31],"more":[22],"data":[23],"is":[24],"better,":[25],"in":[26],"this":[27,64],"paper":[28],"we":[29],"show":[30],"a":[32,36,50,54],"model":[33,51],"trained":[34,52],"on":[35,53],"carefully-chosen":[37],"subset":[38,65],"speakers":[40],"from":[41],"LibriTTS":[42],"provides":[43],"significantly":[44],"better":[45],"synthetic":[47],"speech":[48],"than":[49],"larger":[55],"set.":[56],"We":[57],"propose":[58],"an":[59],"unsupervised":[60],"methodology":[61],"to":[62],"find":[63],"by":[66],"clustering":[67],"per-speaker":[68],"acoustic":[69],"representations.":[70]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
