{"id":"https://openalex.org/W4403784288","doi":"https://doi.org/10.1109/icassp55912.2026.11462862","title":"Emotional Dimension Control in Language Model-Based Text-To-Speech: Spanning a Broad Spectrum of Human Emotions","display_name":"Emotional Dimension Control in Language Model-Based Text-To-Speech: Spanning a Broad Spectrum of Human Emotions","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W4403784288","doi":"https://doi.org/10.1109/icassp55912.2026.11462862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11462862","doi":"https://doi.org/10.1109/icassp55912.2026.11462862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462862","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.16681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035969577","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-3285-9405","observed_orcids":["https://orcid.org/0000-0002-3285-9405"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904472","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-9599-2676","observed_orcids":["https://orcid.org/0000-0002-9599-2676"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,United States of America","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217727","display_name":"Dianwen Ng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758307","display_name":"Shengkui Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116592778","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-2227-075X","observed_orcids":["https://orcid.org/0000-0003-2227-075X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.5469,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92567162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"17257","last_page":"17261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9839000105857849,"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":0.9839000105857849,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.015200000256299973,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0005000000237487257,"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/pleasure-arousal-dominance","display_name":"pleasure-arousal-dominance","score":0.7519999742507935},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"emotional expression","score":0.45100000500679016},{"id":"https://openalex.org/keywords/speech-naturalness","display_name":"speech naturalness","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7694922685623169},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.6279913187026978},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5898356437683105},{"id":"https://openalex.org/C3020442560","wikidata":"https://www.wikidata.org/wiki/Q4971815","display_name":"Broad spectrum","level":2,"score":0.5463160276412964},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4666481018066406},{"id":"https://openalex.org/C2779641649","wikidata":"https://www.wikidata.org/wiki/Q18377767","display_name":"Human Dimension","level":3,"score":0.44364845752716064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42540568113327026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25239089131355286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23098888993263245},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.12972623109817505},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11977320909500122},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.09392091631889343},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C169437150","wikidata":"https://www.wikidata.org/wiki/Q8458","display_name":"Human rights","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp55912.2026.11462862","doi":"https://doi.org/10.1109/icassp55912.2026.11462862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462862","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.16681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16681","pdf_url":"https://arxiv.org/pdf/2409.16681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2409.16681","doi":"https://doi.org/10.48550/arxiv.2409.16681","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.16681","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.16681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16681","pdf_url":"https://arxiv.org/pdf/2409.16681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403784288.pdf","grobid_xml":"https://content.openalex.org/works/W4403784288.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400615667","https://openalex.org/W4408354728","https://openalex.org/W4402115961","https://openalex.org/W4417092535","https://openalex.org/W4283771593","https://openalex.org/W4412623335","https://openalex.org/W4409474293","https://openalex.org/W4415134521","https://openalex.org/W4415747857","https://openalex.org/W3160329778"],"abstract_inverted_index":{"Emotional":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3],"struggle":[4],"to":[5,14,131],"capture":[6],"the":[7,15,22,81,91,98],"full":[8],"spectrum":[9],"of":[10,18,25,46],"human":[11],"emotions":[12],"due":[13],"inherent":[16],"complexity":[17],"emotional":[19,47,69,92,122],"expressions":[20],"and":[21,60,111,124,128],"limited":[23],"coverage":[24],"existing":[26],"emotion":[27,75,106],"labels.":[28],"To":[29,63],"address":[30],"this,":[31,65],"we":[32,66],"propose":[33],"a":[34,43],"language":[35],"model-based":[36],"TTS":[37,99],"framework":[38,100,117],"that":[39,72,115],"synthesizes":[40],"speech":[41,78],"across":[42],"broad":[44],"range":[45],"styles.":[48],"Our":[49],"approach":[50],"enables":[51],"flexible":[52],"user":[53],"control":[54],"along":[55],"three":[56],"continuous":[57],"dimensions\u2014pleasure,":[58],"arousal,":[59],"dominance":[61],"(PAD).":[62],"enable":[64],"train":[67],"an":[68],"dimension":[70,93],"predictor":[71,94],"maps":[73],"categorical":[74,96],"labels":[76,107],"in":[77,85],"datasets":[79],"into":[80],"PAD":[82],"space,":[83],"grounded":[84],"established":[86],"psychological":[87],"research.":[88],"Importantly,":[89],"while":[90],"leverages":[95],"labels,":[97],"itself":[101],"does":[102],"not":[103],"require":[104],"explicit":[105],"during":[108],"training.":[109],"Objective":[110],"subjective":[112],"evaluations":[113],"demonstrate":[114],"our":[116],"effectively":[118],"generates":[119],"more":[120],"expressive":[121],"styles":[123],"enhances":[125],"both":[126],"naturalness":[127],"diversity":[129],"compared":[130],"baselines.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-10-26T00:00:00"}
