{"id":"https://openalex.org/W3015841875","doi":"https://doi.org/10.1109/icassp40776.2020.9053732","title":"Emotional Speech Synthesis with Rich and Granularized Control","display_name":"Emotional Speech Synthesis with Rich and Granularized Control","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015841875","doi":"https://doi.org/10.1109/icassp40776.2020.9053732","mag":"3015841875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053732","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/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Se-Yun Um","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006261553","display_name":"Sangshin Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangshin Oh","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009622431","display_name":"Kyungguen Byun","orcid":"https://orcid.org/0000-0002-4707-5371"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungguen Byun","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001612","display_name":"Inseon Jang","orcid":"https://orcid.org/0000-0003-2237-2668"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseon Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institution, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institution, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111450648","display_name":"Chunghyun Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"ChungHyun Ahn","raw_affiliation_strings":["Electronics and Telecommunications Research Institution, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institution, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074612173"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":7.5559,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.97788947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7254","last_page":"7258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965000152587891,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.8149596452713013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975340247154236},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6434653997421265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5915055274963379},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5900825262069702},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5882196426391602},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.513873815536499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.355508029460907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17473626136779785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07093027234077454}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.8149596452713013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975340247154236},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6434653997421265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5915055274963379},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5900825262069702},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5882196426391602},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.513873815536499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.355508029460907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17473626136779785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07093027234077454},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053732","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":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1902237438","https://openalex.org/W2049686551","https://openalex.org/W2062989416","https://openalex.org/W2102003408","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2134973740","https://openalex.org/W2187089797","https://openalex.org/W2327501763","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2766406951","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2945993525","https://openalex.org/W2949382160","https://openalex.org/W2963403868","https://openalex.org/W2963712897","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964281804","https://openalex.org/W2964308564","https://openalex.org/W2966387353","https://openalex.org/W4251742697","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6679436768","https://openalex.org/W6734815144","https://openalex.org/W6739901393","https://openalex.org/W6746238782","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2164760767","https://openalex.org/W4205698120"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,9,38,79],"effective":[4,80],"emotion":[5,23,56,65,90],"control":[6,16],"method":[7],"for":[8],"end-to-end":[10],"text-to-speech":[11],"(TTS)":[12],"system.":[13],"To":[14,67],"flexibly":[15],"the":[17,33,45,51,54,63,70,85,111,114,118],"distinct":[18],"characteristic":[19],"of":[20,72,87,97,105,113],"a":[21,73,88],"target":[22,55,74,89],"category,":[24],"it":[25],"is":[26],"essential":[27],"to":[28,44,53,62,91,95,117],"determine":[29],"embedding":[30,46],"vectors":[31,47],"representing":[32],"TTS":[34],"input.":[35],"We":[36],"introduce":[37,78],"inter-to-intra":[39],"emotional":[40,106],"distance":[41,52,61],"ratio":[42],"algorithm":[43,116],"that":[48,83,96],"can":[49],"minimize":[50],"category":[57],"while":[58],"maximizing":[59],"its":[60],"other":[64],"categories.":[66],"further":[68],"enhance":[69],"expressiveness":[71,107],"speech,":[75],"we":[76],"also":[77],"interpolation":[81],"technique":[82],"enables":[84],"intensity":[86],"be":[92],"gradually":[93],"changed":[94],"neutral":[98],"speech.":[99],"Subjective":[100],"evaluation":[101],"results":[102],"in":[103],"terms":[104],"and":[108],"controllability":[109],"show":[110],"superiority":[112],"proposed":[115],"conventional":[119],"methods.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}