{"id":"https://openalex.org/W3015719316","doi":"https://doi.org/10.1109/icassp40776.2020.9053255","title":"Emotional Voice Conversion Using Multitask Learning with Text-To-Speech","display_name":"Emotional Voice Conversion Using Multitask Learning with Text-To-Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015719316","doi":"https://doi.org/10.1109/icassp40776.2020.9053255","mag":"3015719316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100452223","display_name":"Taeho Kim","orcid":"https://orcid.org/0000-0003-4522-5388"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","KR"],"is_corresponding":true,"raw_author_name":"Tae-Ho Kim","raw_affiliation_strings":["KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014009200","display_name":"Sungjae Cho","orcid":"https://orcid.org/0000-0003-2547-095X"},"institutions":[{"id":"https://openalex.org/I2800747041","display_name":"Korea Aerospace Research Institute","ror":"https://ror.org/037pqnq23","country_code":"KR","type":"funder","lineage":["https://openalex.org/I2800747041","https://openalex.org/I2801339556","https://openalex.org/I4387152098","https://openalex.org/I4412460384"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjae Cho","raw_affiliation_strings":["Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea","KAIST, Information and Electronics Research Institute, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I878022262","https://openalex.org/I2800747041"]},{"raw_affiliation_string":"KAIST, Information and Electronics Research Institute, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784669","display_name":"Shinkook Choi","orcid":"https://orcid.org/0000-0002-9617-2418"},"institutions":[{"id":"https://openalex.org/I2800747041","display_name":"Korea Aerospace Research Institute","ror":"https://ror.org/037pqnq23","country_code":"KR","type":"funder","lineage":["https://openalex.org/I2800747041","https://openalex.org/I2801339556","https://openalex.org/I4387152098","https://openalex.org/I4412460384"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shinkook Choi","raw_affiliation_strings":["Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea","KAIST, Information and Electronics Research Institute, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Information and Electronics Research Institute,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I878022262","https://openalex.org/I2800747041"]},{"raw_affiliation_string":"KAIST, Information and Electronics Research Institute, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002725756","display_name":"Sejik Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sejik Park","raw_affiliation_strings":["KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616676","display_name":"Soo-Young Lee","orcid":"https://orcid.org/0000-0003-0776-5084"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Soo-Young Lee","raw_affiliation_strings":["KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KI for Artificial Intelligence,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"KAIST, KI for Artificial Intelligence, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100452223"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210164862"],"apc_list":null,"apc_paid":null,"fwci":2.3454,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.90631551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7774","last_page":"7778"},"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":0.9944000244140625,"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/T11309","display_name":"Music and Audio Processing","score":0.9944000244140625,"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":0.7402187585830688},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6781987547874451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.648065984249115},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6277121305465698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.535333514213562},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5043033361434937},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46079331636428833},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44422829151153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43897825479507446},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.43176645040512085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15687215328216553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402187585830688},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6781987547874451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.648065984249115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6277121305465698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.535333514213562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5043033361434937},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46079331636428833},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44422829151153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43897825479507446},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.43176645040512085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15687215328216553},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W186286710","https://openalex.org/W1509691205","https://openalex.org/W2010910318","https://openalex.org/W2013996527","https://openalex.org/W2120605154","https://openalex.org/W2133564696","https://openalex.org/W2157412983","https://openalex.org/W2740504963","https://openalex.org/W2770743791","https://openalex.org/W2795109282","https://openalex.org/W2883743124","https://openalex.org/W2888922217","https://openalex.org/W2892140764","https://openalex.org/W2897353073","https://openalex.org/W2901254300","https://openalex.org/W2911929781","https://openalex.org/W2944711403","https://openalex.org/W2950542544","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W3099078140","https://openalex.org/W3102905810","https://openalex.org/W4295731579","https://openalex.org/W6679434410","https://openalex.org/W6736996214","https://openalex.org/W6746238782","https://openalex.org/W6754925833","https://openalex.org/W6762492278"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W3013209356","https://openalex.org/W2803309984","https://openalex.org/W2883195674","https://openalex.org/W2072736607","https://openalex.org/W2274463100","https://openalex.org/W2125171914","https://openalex.org/W3080374445","https://openalex.org/W2964790801","https://openalex.org/W1522215732"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"is":[3,79,86],"a":[4,11,69,115],"task":[5],"that":[6,72,129],"alters":[7],"the":[8,19,31,58,94,120,135],"voice":[9,70,122],"of":[10,60],"person":[12],"to":[13,44,88,118,123,133],"suit":[14],"different":[15],"styles":[16],"while":[17],"conserving":[18],"linguistic":[20,38,90,136],"content.":[21,137],"Previous":[22],"state-of-the-art":[23],"technology":[24],"used":[25],"in":[26],"VC":[27,85,111],"was":[28,41,64,127],"based":[29],"on":[30,110,114],"sequence-to-sequence":[32],"(seq2seq)":[33],"model,":[34],"which":[35],"could":[36],"lose":[37],"information.":[39,108],"There":[40],"an":[42],"attempt":[43],"overcome":[45],"this":[46,52,67],"problem":[47],"using":[48,61,82],"textual":[49],"supervision;":[50],"however,":[51],"required":[53],"explicit":[54,102],"alignment,":[55],"and":[56,92],"therefore":[57],"benefit":[59],"seq2seq":[62],"model":[63],"lost.":[65],"In":[66],"study,":[68],"converter":[71],"utilizes":[73],"multitask":[74,83,130],"learning":[75,131],"with":[76],"text-to-speech":[77],"(TTS)":[78],"presented.":[80],"By":[81],"learning,":[84],"expected":[87],"capture":[89],"information":[91],"preserve":[93,134],"training":[95],"stability.":[96],"This":[97],"method":[98],"does":[99],"not":[100],"require":[101],"alignment":[103],"for":[104],"capturing":[105],"abundant":[106],"text":[107],"Experiments":[109],"were":[112],"performed":[113],"male-Korean-emotional-text-speech":[116],"dataset":[117],"convert":[119],"neutral":[121],"emotional":[124],"voice.":[125],"It":[126],"shown":[128],"helps":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}