{"id":"https://openalex.org/W4392904615","doi":"https://doi.org/10.1109/icassp48485.2024.10445996","title":"Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis","display_name":"Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904615","doi":"https://doi.org/10.1109/icassp48485.2024.10445996"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.09171","any_repository_has_fulltext":true},"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, Shenzhen (CUHK-Shenzhen),School of Data Science,China","Shenzhen Research Institute of Big Data, Shenzhen, China","School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654458","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-7869-4474"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group,Singapore","Alibaba Group, Speech Lab of DAMO Academy, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group,Singapore","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy, 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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China","Shenzhen Research Institute of Big Data, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["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, Shenzhen (CUHK-Shenzhen),School of Data Science,China","School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China","Shenzhen Research Institute of Big Data, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2768,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95029337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10601","last_page":"10605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/prosody","display_name":"Prosody","score":0.7703814506530762},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7149319052696228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973901987075806},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.546805739402771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416735410690308},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5277546048164368},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5039576888084412},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4826277196407318},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.47770002484321594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46875548362731934},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42737525701522827}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7703814506530762},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7149319052696228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973901987075806},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.546805739402771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416735410690308},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5277546048164368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5039576888084412},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4826277196407318},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.47770002484321594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46875548362731934},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42737525701522827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.09171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.09171","pdf_url":"https://arxiv.org/pdf/2405.09171","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.09171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.09171","pdf_url":"https://arxiv.org/pdf/2405.09171","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"},{"id":"https://openalex.org/G62282921","display_name":null,"funder_award_id":"Grant No. 62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904615.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W388732865","https://openalex.org/W1488156371","https://openalex.org/W1522301498","https://openalex.org/W1566289585","https://openalex.org/W1581458799","https://openalex.org/W2108827278","https://openalex.org/W2119821739","https://openalex.org/W2150791533","https://openalex.org/W2294130536","https://openalex.org/W2747874407","https://openalex.org/W2794490148","https://openalex.org/W2885800352","https://openalex.org/W2894821115","https://openalex.org/W2896457183","https://openalex.org/W3008691130","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3134835907","https://openalex.org/W3163573274","https://openalex.org/W3174758275","https://openalex.org/W4205742757","https://openalex.org/W4210777104","https://openalex.org/W4221147462","https://openalex.org/W4226230180","https://openalex.org/W4296068816","https://openalex.org/W4296069154","https://openalex.org/W4297841375","https://openalex.org/W4313316128","https://openalex.org/W4323896824","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6634507583","https://openalex.org/W6677973343","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6791320390","https://openalex.org/W6796730497","https://openalex.org/W6840933012","https://openalex.org/W6990839660","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"It":[0],"remains":[1],"a":[2,21,40,80],"challenge":[3],"to":[4,38,78],"effectively":[5,46],"control":[6,103],"the":[7,26,65,71,76,90,98,107,116,119],"emotion":[8,42,105,125],"rendering":[9],"in":[10,122],"text-to-speech":[11],"(TTS)":[12],"synthesis.":[13],"Prior":[14],"studies":[15],"have":[16],"primarily":[17],"focused":[18],"on":[19],"learning":[20],"global":[22],"prosodic":[23],"representation":[24],"at":[25,52,97],"utterance":[27],"level,":[28],"which":[29],"strongly":[30],"correlates":[31],"with":[32],"linguistic":[33,85],"prosody.":[34,86],"Our":[35],"goal":[36],"is":[37,68],"construct":[39],"hierarchical":[41,66],"distribution":[43],"(ED)":[44],"that":[45],"encapsulates":[47],"intensity":[48],"variations":[49],"of":[50,55,104,118,124],"emotions":[51],"various":[53],"levels":[54],"granularity,":[56],"encompassing":[57],"phonemes,":[58],"words,":[59],"and":[60,74,84,112,127],"utterances.":[61],"During":[62],"TTS":[63,91],"training,":[64],"ED":[67],"extracted":[69],"from":[70],"ground-truth":[72],"audio":[73],"guides":[75],"predictor":[77],"establish":[79],"connection":[81],"between":[82],"emotional":[83,94],"At":[87],"run-time":[88],"inference,":[89],"model":[92],"generates":[93],"speech":[95,108],"and,":[96],"same":[99],"time,":[100],"provides":[101],"quantitative":[102],"over":[106],"constituents.":[109],"Both":[110],"objective":[111],"subjective":[113],"evaluations":[114],"validate":[115],"effectiveness":[117],"proposed":[120],"framework":[121],"terms":[123],"prediction":[126],"control.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}