{"id":"https://openalex.org/W2291468875","doi":"https://doi.org/10.21437/interspeech.2012-598","title":"Towards an unsupervised speaking style voice building framework: multi.style speaker diarization","display_name":"Towards an unsupervised speaking style voice building framework: multi.style speaker diarization","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2291468875","doi":"https://doi.org/10.21437/interspeech.2012-598","mag":"2291468875"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://oa.upm.es/20407/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012509117","display_name":"Beatriz Mart\u00ednez-Gonz\u00e1lez","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Beatriz Martinez-Gonzalez","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031279073","display_name":"Ver\u00f3nica L\u00f3pez-Lude\u00f1a","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Veronica Lopez\u2013Lude\u00f1a","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028386517","display_name":"Javier Ferreiros","orcid":"https://orcid.org/0000-0001-8834-3080"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Ferreiros","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051480712","display_name":"Juan Manuel Montero","orcid":"https://orcid.org/0000-0002-7908-5400"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan M. Montero","raw_affiliation_strings":["Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2278","last_page":"2281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9977999925613403,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9570574164390564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721255421638489},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7332479953765869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6715986728668213},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5060500502586365},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4470668137073517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37190306186676025}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9570574164390564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721255421638489},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7332479953765869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6715986728668213},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5060500502586365},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4470668137073517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37190306186676025},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2012-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:oa.upm.es:20407","is_oa":true,"landing_page_url":"http://oa.upm.es/20407/","pdf_url":"http://oa.upm.es/20407/","source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association | InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association | 09/09/2012 - 13/09/2012 | Portland, Oregon","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ba526ac8-3b40-47e6-8a80-0fcdadae2575","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2012","pdf_url":"https://www.pure.ed.ac.uk/ws/files/14269570/LorenzoTrueba_MartinezGonzalez_2012_Towards_an_Unsuperviased_Speaking_Style_Voice_Building_Framework.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.4376","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.4376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/AG-113Tow-12.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/ba526ac8-3b40-47e6-8a80-0fcdadae2575","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ba526ac8-3b40-47e6-8a80-0fcdadae2575","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":"Lorenzo, J, Martinez, B, Barra-Chicote, R, Lopez-Ludena, V, Ferreiros, J, Yamagishi, J & Montero, J M 2012, Towards an Unsupervised Speaking Style Voice Building Framework : Multi-Style Speaker Diarization. in Proc. Interspeech 2012 : 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012. < http://www.isca-speech.org/archive/interspeech_2012 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:oa.upm.es:20407","is_oa":true,"landing_page_url":"http://oa.upm.es/20407/","pdf_url":"http://oa.upm.es/20407/","source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association | InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association | 09/09/2012 - 13/09/2012 | Portland, Oregon","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2291468875.pdf","grobid_xml":"https://content.openalex.org/works/W2291468875.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1491238342","https://openalex.org/W1583007810","https://openalex.org/W1987878469","https://openalex.org/W2081074144","https://openalex.org/W2145880678","https://openalex.org/W2153914468","https://openalex.org/W2159150199","https://openalex.org/W2309282333","https://openalex.org/W2341824394","https://openalex.org/W2395865858","https://openalex.org/W2400063444","https://openalex.org/W2403771732","https://openalex.org/W2620757702","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Current":[0],"text-to-speech":[1],"systems":[2,32],"are":[3,93],"developed":[4],"using":[5],"studio-recorded":[6],"speech":[7],"in":[8],"a":[9,27,72,82],"neutral":[10],"style":[11],"or":[12,110],"based":[13],"on":[14,56],"acted":[15],"emotions.":[16],"However,":[17],"the":[18,64,68,76,79,91,100],"proliferation":[19],"of":[20,30,67,81],"media":[21],"sharing":[22],"sites":[23],"would":[24],"allow":[25],"developing":[26],"new":[28],"generation":[29],"speech-based":[31],"which":[33],"could":[34],"cope":[35],"with":[36,48],"spontaneous":[37,102],"and":[38,51,103],"styled":[39],"speech.":[40],"This":[41],"paper":[42,77],"proposes":[43],"an":[44],"architecture":[45],"to":[46,62],"deal":[47],"realistic":[49],"recordings":[50],"carries":[52],"out":[53],"some":[54],"experiments":[55],"unsupervised":[57],"speaker":[58,65,74],"diarization.":[59],"In":[60],"order":[61],"maximize":[63],"purity":[66],"clusters":[69,92],"while":[70],"keeping":[71],"high":[73,86],"coverage,":[75],"evaluates":[78],"F-measure":[80],"diarization":[83],"module,":[84],"achieving":[85],"scores":[87],"(&gt;85%)":[88],"especially":[89],"when":[90],"longer":[94],"than":[95],"30":[96],"seconds,":[97],"even":[98],"for":[99],"more":[101],"expressive":[104],"styles":[105],"(such":[106],"as":[107],"talk":[108],"shows":[109],"sports).":[111]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}