{"id":"https://openalex.org/W3204457821","doi":"https://doi.org/10.1109/taslp.2022.3190715","title":"Decoupling Speaker-Independent Emotions for Voice Conversion via Source-Filter Networks","display_name":"Decoupling Speaker-Independent Emotions for Voice Conversion via Source-Filter Networks","publication_year":2022,"publication_date":"2022-07-14","ids":{"openalex":"https://openalex.org/W3204457821","doi":"https://doi.org/10.1109/taslp.2022.3190715","mag":"3204457821"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3190715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3190715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09829916.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09829916.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077713342","display_name":"Zhaojie Luo","orcid":"https://orcid.org/0000-0002-4173-6319"},"institutions":[{"id":"https://openalex.org/I4210138169","display_name":"Osaka Research Institute of Industrial Science and Technology","ror":"https://ror.org/03r38cy24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210138169"]},{"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":"Zhaojie Luo","raw_affiliation_strings":["Institute of Scientific and Industrial Research, Osaka University, Toyonaka, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4173-6319","affiliations":[{"raw_affiliation_string":"Institute of Scientific and Industrial Research, Osaka University, Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I4210138169","https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083582801","display_name":"Shoufeng Lin","orcid":"https://orcid.org/0000-0002-9508-0706"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shoufeng Lin","raw_affiliation_strings":["School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9508-0706","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, China"],"raw_orcid":"https://orcid.org/0000-0003-4524-7413","affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001122947","display_name":"Jun Baba","orcid":"https://orcid.org/0000-0003-0680-5021"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]},{"id":"https://openalex.org/I4210136457","display_name":"Shibuya (Japan)","ror":"https://ror.org/03t1ztz45","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210136457"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Baba","raw_affiliation_strings":["CyberAgent, Inc., Shibuya-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0680-5021","affiliations":[{"raw_affiliation_string":"CyberAgent, Inc., Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607","https://openalex.org/I4210136457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039236080","display_name":"Yuichiro Yoshikawa","orcid":"https://orcid.org/0000-0002-3484-0361"},"institutions":[{"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":"Yuichiro Yoshikawa","raw_affiliation_strings":["Graduate School of Engineer Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3484-0361","affiliations":[{"raw_affiliation_string":"Graduate School of Engineer Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"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/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":["Graduate School of Engineer Science, Osaka University, Toyonaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineer Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4038,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.8869121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"11","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7654837369918823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.750699520111084},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5553464293479919},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.45870575308799744},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.439815491437912},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41435468196868896},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25052958726882935},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1056414246559143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654837369918823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.750699520111084},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5553464293479919},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.45870575308799744},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.439815491437912},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41435468196868896},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25052958726882935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1056414246559143},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control 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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3190715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3190715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09829916.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3190715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3190715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09829916.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3056003011","display_name":null,"funder_award_id":"JPMJMS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204457821.pdf","grobid_xml":"https://content.openalex.org/works/W3204457821.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1510835889","https://openalex.org/W1588037970","https://openalex.org/W1972076735","https://openalex.org/W1976725440","https://openalex.org/W1999964619","https://openalex.org/W2017425464","https://openalex.org/W2023736093","https://openalex.org/W2040984620","https://openalex.org/W2051487990","https://openalex.org/W2056661291","https://openalex.org/W2077801020","https://openalex.org/W2089624917","https://openalex.org/W2092804630","https://openalex.org/W2098986833","https://openalex.org/W2099471712","https://openalex.org/W2105160541","https://openalex.org/W2108601574","https://openalex.org/W2116628589","https://openalex.org/W2120605154","https://openalex.org/W2120687203","https://openalex.org/W2128070398","https://openalex.org/W2161736993","https://openalex.org/W2164241094","https://openalex.org/W2187089797","https://openalex.org/W2293634267","https://openalex.org/W2294351487","https://openalex.org/W2319003035","https://openalex.org/W2396025094","https://openalex.org/W2399915284","https://openalex.org/W2471520273","https://openalex.org/W2511640485","https://openalex.org/W2517513811","https://openalex.org/W2518312472","https://openalex.org/W2562848127","https://openalex.org/W2598656683","https://openalex.org/W2610171128","https://openalex.org/W2740504963","https://openalex.org/W2744580635","https://openalex.org/W2765486990","https://openalex.org/W2774848319","https://openalex.org/W2795783309","https://openalex.org/W2809859618","https://openalex.org/W2888011686","https://openalex.org/W2889482935","https://openalex.org/W2914461061","https://openalex.org/W2919115771","https://openalex.org/W2945478979","https://openalex.org/W2946809691","https://openalex.org/W2950542544","https://openalex.org/W2963539064","https://openalex.org/W2964243274","https://openalex.org/W2990440871","https://openalex.org/W2997663825","https://openalex.org/W3004402693","https://openalex.org/W3015959238","https://openalex.org/W3020570669","https://openalex.org/W3025680351","https://openalex.org/W3034794073","https://openalex.org/W3163573274","https://openalex.org/W4205742757","https://openalex.org/W4320013936","https://openalex.org/W6743094995","https://openalex.org/W6745289305","https://openalex.org/W6749954789","https://openalex.org/W6762533536","https://openalex.org/W6776390925"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2559837139","https://openalex.org/W2541680182","https://openalex.org/W2407342067"],"abstract_inverted_index":{"Emotional":[0,87],"voice":[1,9],"conversion":[2,139],"(VC)":[3],"aims":[4],"to":[5,10,43,66,91,135],"convert":[6],"a":[7,84,129,144,166],"neutral":[8,56],"an":[11],"emotional":[12,28,63,180],"one":[13],"while":[14],"retaining":[15],"the":[16,25,41,55,62,67,75,101,120,138,150,161,175],"linguistic":[17],"information":[18,33,131],"and":[19,103,119,173],"speaker":[20,37],"identity.":[21],"We":[22],"note":[23],"that":[24,124,160],"decoupling":[26,53],"of":[27,50,71,95,110],"features":[29],"from":[30,99],"other":[31],"speech":[32,51,57],"(such":[34],"as":[35],"content,":[36],"identity,":[38],"etc.)":[39],"is":[40,155],"key":[42],"achieving":[44],"promising":[45],"performance.":[46],"Some":[47],"recent":[48],"attempts":[49],"representation":[52],"on":[54,61,149],"cannot":[58],"work":[59],"well":[60],"speech,":[64],"due":[65],"more":[68],"complex":[69],"entanglement":[70],"acoustic":[72],"properties":[73],"in":[74,178],"latter.":[76],"To":[77],"address":[78],"this":[79],"problem,":[80],"here":[81],"we":[82],"propose":[83],"novel":[85,145],"Source-Filter-based":[86],"VC":[88,181],"model":[89,108],"(SFEVC)":[90],"achieve":[92],"proper":[93],"filtering":[94],"speaker-independent":[96,179],"emotion":[97,113],"cues":[98],"both":[100],"timbre":[102],"pitch":[104],"features.":[105],"Our":[106],"SFEVC":[107,163],"consists":[109],"multi-channel":[111],"encoders,":[112,115,118],"separate":[114],"pre-trained":[116],"speaker-dependent":[117],"corresponding":[121],"decoder.":[122],"Note":[123],"all":[125,171],"encoder":[126],"modules":[127],"adopt":[128],"designed":[130],"bottleneck":[132],"auto-encoder.":[133],"Additionally,":[134],"further":[136],"improve":[137],"quality":[140],"for":[141],"various":[142],"emotions,":[143],"training":[146,168],"strategy":[147,169],"based":[148],"2D":[151],"Valence-Arousal":[152],"(VA)":[153],"space":[154],"proposed.":[156],"Experimental":[157],"results":[158],"show":[159],"proposed":[162],"along":[164],"with":[165,182],"VA":[167],"outperforms":[170],"baselines":[172],"achieves":[174],"state-of-the-art":[176],"performance":[177],"nonparallel":[183],"data.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}