{"id":"https://openalex.org/W10800834","doi":"https://doi.org/10.21437/interspeech.2011-268","title":"One-to-many voice conversion based on tensor representation of speaker space","display_name":"One-to-many voice conversion based on tensor representation of speaker space","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W10800834","doi":"https://doi.org/10.21437/interspeech.2011-268","mag":"10800834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/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":"Daisuke Saito","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009636601","display_name":"Keisuke Yamamoto","orcid":"https://orcid.org/0000-0002-6323-9540"},"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":"Keisuke Yamamoto","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","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":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"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":"Keikichi Hirose","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.992900013923645,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6275792717933655},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5775351524353027},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5638993978500366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5608552098274231},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5510748028755188},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5158090591430664},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45021066069602966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15377652645111084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6275792717933655},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5775351524353027},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5638993978500366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5608552098274231},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5510748028755188},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5158090591430664},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45021066069602966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15377652645111084},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.416","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.416","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/2011/INTERSPEECH_p653-656_t2011-8.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W1588266896","https://openalex.org/W1603790919","https://openalex.org/W1950777589","https://openalex.org/W1963826206","https://openalex.org/W1965255698","https://openalex.org/W2007023536","https://openalex.org/W2009377577","https://openalex.org/W2009396100","https://openalex.org/W2013912476","https://openalex.org/W2049686551","https://openalex.org/W2113055885","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2136879537","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2165108269"],"related_works":["https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2161543916"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,60,94,129],"novel":[4],"approach":[5,168],"to":[6,56,140],"flexible":[7],"control":[8],"of":[9,15,23,32,79,81,97,100,108,117,131,147,161,164,174,182,187,194],"speaker":[10,16,57,61,83,87,90,110,125,153],"characteristics":[11],"using":[12],"tensor":[13,115,159,206],"representation":[14],"space.":[17],"In":[18,52,85,102,121],"voice":[19,29,183,189,200],"conversion":[20,24,40,190],"studies,":[21],"realization":[22],"from/to":[25],"an":[26,44,171],"arbitrary":[27],"speaker\u2019s":[28],"is":[30,63,91,126,155],"one":[31],"the":[33,53,76,82,86,109,114,133,136,141,145,148,152,158,162,165,180,192,195],"important":[34],"objectives.":[35],"For":[36],"this":[37,103],"purpose,":[38],"eigenvoice":[39,45],"(EVC)":[41],"based":[42,65],"on":[43,66],"Gaussian":[46,142,202],"mixture":[47,203],"model":[48],"(EV-GMM)":[49],"was":[50],"proposed.":[51],"EVC,":[54],"similarly":[55],"recognition":[58],"approaches,":[59],"space":[62,111,154],"constructed":[64],"GMM":[67],"supervectors":[68],"which":[69,132],"are":[70],"high-dimensional":[71],"vectors":[72,78],"derived":[73,156],"by":[74,93,112,157],"concatenating":[75],"mean":[77,149],"each":[80,89,124],"GMMs.":[84],"space,":[88],"represented":[92,127],"small":[95],"number":[96],"weight":[98],"parameters":[99],"eigen-supervectors.":[101],"paper,":[104],"we":[105],"revisit":[106],"construction":[107],"introducing":[113],"analysis":[116,160],"training":[118],"data":[119],"set.":[120],"our":[122],"approach,":[123],"as":[128],"matrix":[130],"row":[134],"and":[135,144,151,177],"column":[137],"respectively":[138],"correspond":[139],"component":[143],"dimension":[146],"vector,":[150],"set":[163],"matrices.":[166],"Our":[167],"can":[169],"solve":[170],"inherent":[172],"problem":[173],"supervector":[175],"representation,":[176],"it":[178],"improves":[179],"performance":[181],"conversion.":[184],"Experimental":[185],"results":[186],"oneto-many":[188],"demonstrate":[191],"effectiveness":[193],"proposed":[196],"approach.":[197],"Index":[198],"Terms:":[199],"conversion,":[201],"model,":[204],"eigenvoice,":[205],"analysis,":[207],"Tucker":[208],"decomposition":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}