{"id":"https://openalex.org/W4391021367","doi":"https://doi.org/10.1109/asru57964.2023.10389651","title":"Using Joint Training Speaker Encoder With Consistency Loss to Achieve Cross-Lingual Voice Conversion and Expressive Voice Conversion","display_name":"Using Joint Training Speaker Encoder With Consistency Loss to Achieve Cross-Lingual Voice Conversion and Expressive Voice Conversion","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021367","doi":"https://doi.org/10.1109/asru57964.2023.10389651"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5027839955","display_name":"Houjian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Houjian Guo","raw_affiliation_strings":["Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","Graduate School of Engineering Science, Osaka University, Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905297","display_name":"Chaoran Liu","orcid":"https://orcid.org/0000-0003-3789-2981"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":["Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Carlos Toshinori Ishi","raw_affiliation_strings":["Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Japan","Advanced Telecommunications Research Institute International, Japan","Graduate School of Engineering Science, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9836000204086304,"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/speech-recognition","display_name":"Speech recognition","score":0.7242938280105591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7123009562492371},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6157733201980591},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.609778106212616},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5842137336730957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4310082793235779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2812999486923218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0924505889415741}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7242938280105591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123009562492371},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6157733201980591},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.609778106212616},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5842137336730957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4310082793235779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2812999486923218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0924505889415741},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2535388113","https://openalex.org/W2810914326","https://openalex.org/W2902070858","https://openalex.org/W2936842814","https://openalex.org/W2938583109","https://openalex.org/W2946200149","https://openalex.org/W2963242190","https://openalex.org/W2969049672","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3033411150","https://openalex.org/W3083423753","https://openalex.org/W3098557217","https://openalex.org/W3135654121","https://openalex.org/W3158762648","https://openalex.org/W3165478005","https://openalex.org/W3168719651","https://openalex.org/W3197991492","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4205742757","https://openalex.org/W4225892118","https://openalex.org/W4226320669","https://openalex.org/W4226474318","https://openalex.org/W4286747238","https://openalex.org/W4311000453","https://openalex.org/W4313679638","https://openalex.org/W4372260053","https://openalex.org/W4375869015","https://openalex.org/W4385823191","https://openalex.org/W6753049143","https://openalex.org/W6763832098","https://openalex.org/W6767245602","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,16,29,33],"systems":[2],"have":[3],"made":[4],"significant":[5],"advancements":[6],"in":[7,13,21],"terms":[8],"of":[9,96,125],"naturalness":[10],"and":[11,30,51,87,121],"similarity":[12,82],"common":[14],"voice":[15,28,32,66],"tasks.":[17],"However,":[18],"their":[19],"performance":[20],"more":[22],"complex":[23],"tasks":[24],"such":[25],"as":[26,106],"cross-lingual":[27,57,65],"expressive":[31],"remains":[34],"imperfect.":[35],"In":[36],"this":[37],"study,":[38],"we":[39,69,101],"propose":[40],"a":[41,46,71],"novel":[42],"approach":[43],"that":[44],"combines":[45],"joint":[47,77,98],"training":[48],"speaker":[49,72,99,119],"encoder":[50],"content":[52,108],"features":[53],"extracted":[54],"from":[55],"the":[56,76,81,84,88,94,97,103,107,112,118,122,126],"speech":[58,86],"recognition":[59],"model":[60,113],"Whisper":[61],"to":[62,75,114],"achieve":[63],"high-quality":[64],"conversion.":[67],"Additionally,":[68],"introduce":[70],"consistency":[73],"loss":[74],"encoder,":[78,100],"which":[79,110],"improves":[80],"between":[83],"converted":[85],"reference":[89,127],"speech.":[90,128],"To":[91],"further":[92],"explore":[93],"capabilities":[95],"use":[102],"Phonetic":[104],"posteriorgram":[105],"feature,":[109],"enables":[111],"effectively":[115],"reproduce":[116],"both":[117],"characteristics":[120],"emotional":[123],"aspects":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}