{"id":"https://openalex.org/W4406860647","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848721","title":"Fine-Grained Quantitative Emotion Editing for Speech Generation","display_name":"Fine-Grained Quantitative Emotion Editing for Speech Generation","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860647","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848721"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5108413182","display_name":"Sho Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sho Inoue","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654458","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-7869-4474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group,Speech Lab, Institute for Intelligent Computing,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab, Institute for Intelligent Computing,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328312","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-7897-2024"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science, Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5273,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8634964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9689000248908997,"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":0.9689000248908997,"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/computer-science","display_name":"Computer science","score":0.7111549377441406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4984593391418457},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3401685357093811},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3293984830379486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111549377441406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4984593391418457},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3401685357093811},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3293984830379486}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W113106864","https://openalex.org/W1581458799","https://openalex.org/W1965069145","https://openalex.org/W2074788634","https://openalex.org/W2085662862","https://openalex.org/W2107860279","https://openalex.org/W2119821739","https://openalex.org/W2294130536","https://openalex.org/W2330979245","https://openalex.org/W2517513811","https://openalex.org/W2609635007","https://openalex.org/W2747874407","https://openalex.org/W2791322592","https://openalex.org/W2803098682","https://openalex.org/W2963047186","https://openalex.org/W3008691130","https://openalex.org/W3025680351","https://openalex.org/W3096939667","https://openalex.org/W3116819420","https://openalex.org/W3135644023","https://openalex.org/W3142644187","https://openalex.org/W3146550708","https://openalex.org/W3160329778","https://openalex.org/W3160438760","https://openalex.org/W3163573274","https://openalex.org/W3197216873","https://openalex.org/W4205742757","https://openalex.org/W4210777104","https://openalex.org/W4221147462","https://openalex.org/W4224926192","https://openalex.org/W4225596771","https://openalex.org/W4226230180","https://openalex.org/W4286747238","https://openalex.org/W4297841480","https://openalex.org/W4313316128","https://openalex.org/W4323896824","https://openalex.org/W4372340836","https://openalex.org/W4392904615","https://openalex.org/W4400621957","https://openalex.org/W6605639189","https://openalex.org/W6677973343","https://openalex.org/W6763984584","https://openalex.org/W6990839660"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"It":[0],"remains":[1],"a":[2,39],"significant":[3],"challenge":[4],"how":[5],"to":[6,70],"quantitatively":[7],"control":[8],"the":[9,28,49,64,68,86,90,99,102],"expressiveness":[10],"of":[11,27,51,56,89,101,107],"speech":[12,15,35],"emotion":[13,29,32,41,72,110],"in":[14,34,105],"generation.":[16,36],"In":[17],"this":[18],"work,":[19],"we":[20],"propose":[21],"an":[22],"approach":[23],"for":[24,31],"quantitative":[25,109],"manipulation":[26],"rendering":[30],"editing":[33],"We":[37],"apply":[38],"hierarchical":[40],"distribution":[42],"extractor,":[43],"i.e.":[44],"Hierarchical":[45,58],"ED,":[46],"that":[47],"quantifies":[48],"intensity":[50,73,88],"emotions":[52],"at":[53,74],"different":[54],"levels":[55],"granularity.":[57],"ED":[59],"is":[60],"subsequently":[61],"integrated":[62],"into":[63],"FastSpeech2":[65],"framework,":[66],"guiding":[67],"model":[69],"learn":[71],"phoneme,":[75],"word,":[76],"and":[77,95],"utterance":[78],"levels.":[79],"During":[80],"synthesis,":[81],"users":[82],"can":[83],"manually":[84],"edit":[85],"emotional":[87],"generated":[91],"voices.":[92],"Both":[93],"objective":[94],"subjective":[96],"evaluations":[97],"demonstrate":[98],"effectiveness":[100],"proposed":[103],"network":[104],"terms":[106],"fine-grained":[108],"editing.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}