{"id":"https://openalex.org/W193510348","doi":"https://doi.org/10.21437/interspeech.2010-496","title":"Probabilistic integration of joint density model and speaker model for voice conversion","display_name":"Probabilistic integration of joint density model and speaker model for voice conversion","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W193510348","doi":"https://doi.org/10.21437/interspeech.2010-496","mag":"193510348"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["Nippon Telegraph & Telephone","The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"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":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1728","last_page":"1731"},"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":0.995199978351593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9876999855041504,"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/joint","display_name":"Joint (building)","score":0.7891221046447754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817909717559814},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7090315222740173},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.706326961517334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6397448182106018},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.5363567471504211},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5338574051856995},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5088546276092529},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.47050970792770386},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.4221358597278595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4193936586380005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12216532230377197},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08764269948005676}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7891221046447754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817909717559814},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7090315222740173},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.706326961517334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6397448182106018},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5363567471504211},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5338574051856995},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5088546276092529},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.47050970792770386},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4221358597278595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4193936586380005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12216532230377197},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08764269948005676},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.481","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2010/INTERSPEECH_p1728-1731_t2010-9.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W1588266896","https://openalex.org/W1950777589","https://openalex.org/W1965255698","https://openalex.org/W2041823554","https://openalex.org/W2049686551","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2153057929","https://openalex.org/W2156142001"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362","https://openalex.org/W2136153680","https://openalex.org/W2972577568"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,11,16,37,40,48,56,101,129],"novel":[4,102],"approach":[5,103],"to":[6,46,104],"voice":[7,20,172],"conversion":[8],"using":[9,117],"both":[10,71],"joint":[12,34,77,114,125,174],"density":[13,78,115,126,175],"model":[14,116,127,136],"and":[15,39,133],"speaker":[17,107,135,177],"model.":[18],"In":[19,74],"con-version":[21],"studies,":[22],"approaches":[23],"based":[24],"on":[25,148],"Gaussian":[26],"Mixture":[27],"Model":[28],"(GMM)":[29],"with":[30,64,112,128,137],"probabilistic":[31,118,179],"densities":[32],"of":[33,36,62,89,109,140,156,164],"vectors":[35],"source":[38,150],"target":[41,111],"speakers":[42],"are":[43],"widely":[44],"used":[45],"estimate":[47],"transfor-mation.":[49],"However,":[50],"for":[51,96],"sufficient":[52],"quality,":[53],"they":[54],"require":[55],"parallel":[57,131,166],"corpus":[58,167],"which":[59],"contains":[60],"plenty":[61],"utterances":[63],"the":[65,72,76,87,106,110,113,124,134,141,146,149,154,157,162,165],"same":[66],"lin-guistic":[67],"content":[68],"spoken":[69],"by":[70],"speakers.":[73],"addition,":[75],"GMM":[79,108],"methods":[80],"often":[81],"suffer":[82],"from":[83],"over-training":[84],"ef-fects":[85],"when":[86,161],"amount":[88,163],"training":[90],"data":[91,139],"is":[92,168],"small.":[93,169],"To":[94],"compensate":[95],"these":[97],"problems,":[98],"we":[99],"propose":[100],"integrate":[105],"formulation.":[119],"The":[120],"proposed":[121,158],"method":[122],"trains":[123],"few":[130],"utterances,":[132],"non-parallel":[138],"target,":[142],"independently.":[143],"It":[144],"eases":[145],"burden":[147],"speaker.":[151],"Experiments":[152],"demon-strate":[153],"effectiveness":[155],"method,":[159],"especially":[160],"Index":[170],"Terms:":[171],"conversion,":[173],"model,":[176,178],"unification":[180]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}