{"id":"https://openalex.org/W2963808252","doi":"https://doi.org/10.21437/interspeech.2017-247","title":"Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities","display_name":"Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963808252","doi":"https://doi.org/10.21437/interspeech.2017-247","mag":"2963808252"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-247","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","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/A5023133620","display_name":"Hiroyuki Miyoshi","orcid":"https://orcid.org/0000-0002-3678-1641"},"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":true,"raw_author_name":"Hiroyuki Miyoshi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"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":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"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":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023133620"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":7.79210769,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97373159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1268","last_page":"1272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9503999948501587,"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/T10028","display_name":"Topic Modeling","score":0.9205999970436096,"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/posterior-probability","display_name":"Posterior probability","score":0.8301589488983154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534788846969604},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6961851119995117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6769945621490479},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.579436182975769},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5037054419517517},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4572983682155609},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3714033365249634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3671632409095764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3457508981227875},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.06521293520927429}],"concepts":[{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.8301589488983154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534788846969604},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6961851119995117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6769945621490479},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.579436182975769},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5037054419517517},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4572983682155609},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3714033365249634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3671632409095764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3457508981227875},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.06521293520927429},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-247","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W187033940","https://openalex.org/W1523372075","https://openalex.org/W1540882196","https://openalex.org/W1959608418","https://openalex.org/W1991682319","https://openalex.org/W2049686551","https://openalex.org/W2108501770","https://openalex.org/W2110798204","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2130942839","https://openalex.org/W2142300631","https://openalex.org/W2146502635","https://openalex.org/W2152974894","https://openalex.org/W2156142001","https://openalex.org/W2157331557","https://openalex.org/W2395578248","https://openalex.org/W2396990910","https://openalex.org/W2507912506","https://openalex.org/W2515943672","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2532494225","https://openalex.org/W2546938941","https://openalex.org/W4395958265"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2348743188","https://openalex.org/W4387423451","https://openalex.org/W2902317490","https://openalex.org/W2025460258","https://openalex.org/W2883195674","https://openalex.org/W2072736607","https://openalex.org/W2125171914","https://openalex.org/W3080374445","https://openalex.org/W2964790801"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,97,157],"(VC)":[2],"using":[3,13],"sequence-to-sequence":[4,88],"learning":[5,89],"of":[6],"context":[7,15,24],"posterior":[8,16,25,58,63,95,134],"probabilities":[9,17,26,59,64,135],"is":[10,42],"proposed.Conventional":[11],"VC":[12,34],"shared":[14],"predicts":[18,141],"target":[19,70,94,111,142],"speech":[20,31,71,84,130,138,143],"parameters":[21],"from":[22,28,38,104],"the":[23,29,57,61,78,91,105,110,120,129,137,154,165],"estimated":[27],"source":[30,62,92,106],"parameters.Although":[32],"conventional":[33,124,166],"can":[35],"be":[36],"built":[37],"non-parallel":[39],"data,":[40],"it":[41],"difficult":[43],"to":[44,109,123],"convert":[45],"speaker":[46],"individuality":[47],"such":[48],"as":[49],"phonetic":[50],"property":[51],"and":[52,86,93,101,136],"speaking":[53],"rate":[54],"contained":[55],"in":[56],"because":[60],"are":[65],"directly":[66],"used":[67],"for":[68,119],"predicting":[69],"parameters.In":[72],"this":[73],"work,":[74],"we":[75,113],"assume":[76],"that":[77,132,140,161],"training":[79,117],"data":[80,85],"partly":[81],"include":[82],"parallel":[83],"propose":[87,114],"between":[90],"probabilities.The":[96],"models":[98],"perform":[99],"non-linear":[100],"variable-length":[102],"transformation":[103],"probability":[107,156],"sequence":[108],"one.Further,":[112],"a":[115],"joint":[116],"algorithm":[118],"modules.In":[121],"contrast":[122],"VC,":[125],"which":[126],"separately":[127],"trains":[128,149],"recognition":[131],"estimates":[133],"synthesis":[139],"parameters,":[144],"our":[145,162],"proposed":[146,155],"method":[147],"jointly":[148],"these":[150],"modules":[151],"along":[152],"with":[153],"modules.Experimental":[158],"results":[159],"demonstrate":[160],"approach":[163],"outperforms":[164],"VC.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}