{"id":"https://openalex.org/W4415747857","doi":"https://doi.org/10.1109/lsp.2025.3627104","title":"Prompt-Unseen-Emotion: Mixed Emotional Speech Synthesis With Prompt-LLM Contextual Knowledge","display_name":"Prompt-Unseen-Emotion: Mixed Emotional Speech Synthesis With Prompt-LLM Contextual Knowledge","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415747857","doi":"https://doi.org/10.1109/lsp.2025.3627104"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3627104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627104","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101856962","display_name":"Xiaoxue Gao","orcid":"https://orcid.org/0000-0003-1920-5228"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaoxue Gao","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1920-5228","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102856166","display_name":"Huayun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huayun Zhang","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2528-273X","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0872-5877","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology, and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89100511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"4259","last_page":"4263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.698199987411499,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.698199987411499,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.12800000607967377,"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/T12488","display_name":"Mental Health via Writing","score":0.05260000005364418,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/categorical-variable","display_name":"Categorical variable","score":0.6793000102043152},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.588100016117096},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43630000948905945},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.38659998774528503},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.36329999566078186},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.3499000072479248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708299994468689},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3499000072479248},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2779881370","wikidata":"https://www.wikidata.org/wiki/Q383340","display_name":"Speech community","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25780001282691956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3627104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627104","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W571907995","https://openalex.org/W2039800941","https://openalex.org/W2089989403","https://openalex.org/W2091084672","https://openalex.org/W2950542544","https://openalex.org/W3015841875","https://openalex.org/W3135644023","https://openalex.org/W3146550708","https://openalex.org/W3160329778","https://openalex.org/W3198123658","https://openalex.org/W4205742757","https://openalex.org/W4313155892","https://openalex.org/W4313316128","https://openalex.org/W4319985616","https://openalex.org/W4375869045","https://openalex.org/W4375869364","https://openalex.org/W4382202703","https://openalex.org/W4385822379","https://openalex.org/W4385993826","https://openalex.org/W4393160807","https://openalex.org/W4398152753","https://openalex.org/W4400621957","https://openalex.org/W4402669711","https://openalex.org/W4404792839","https://openalex.org/W4406461501","https://openalex.org/W4406794290","https://openalex.org/W4408354728","https://openalex.org/W4411600219","https://openalex.org/W4415065044"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"expressive":[1,113],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"primarily":[5],"model":[6,75,104],"a":[7,43,120],"limited":[8],"set":[9],"of":[10,116],"categorical":[11,67],"emotions,":[12,21],"whereas":[13],"human":[14],"conversations":[15],"extend":[16],"far":[17],"beyond":[18],"these":[19],"predefined":[20],"making":[22],"it":[23],"essential":[24],"to":[25,48,62,76,105],"explore":[26],"more":[27,33],"diverse":[28],"emotional":[29,51,64,71,87,108],"speech":[30,52,88,114],"generation":[31],"for":[32],"natural":[34],"interactions.":[35],"To":[36],"bridge":[37],"this":[38,40],"gap,":[39],"paper":[41],"proposes":[42],"novel":[44],"prompt-unseen-emotion":[45],"(PUE)":[46],"approach":[47],"generate":[49],"unseen":[50,117],"via":[53],"emotion-guided":[54],"prompt":[55],"learning.PUEis":[56],"trained":[57],"utilizing":[58],"an":[59],"LLM-TTS":[60],"architecture":[61],"ensure":[63],"consistency":[65],"between":[66],"emotion-relevant":[68],"prompts":[69],"and":[70,97],"speech,":[72],"allowing":[73],"the":[74,103],"quantitatively":[77],"capture":[78],"different":[79,107],"emotion":[80,95],"weightings":[81],"per":[82],"utterance.":[83],"During":[84],"inference,":[85],"mixed":[86],"can":[89],"be":[90],"generated":[91],"by":[92],"flexibly":[93],"adjusting":[94],"proportions":[96],"leveraging":[98],"LLM":[99],"contextual":[100],"knowledge,":[101],"enabling":[102],"quantify":[106],"styles.":[109],"Our":[110],"proposedPUEsuccessfully":[111],"facilitates":[112],"synthesis":[115],"emotions":[118],"in":[119],"zero-shot":[121],"setting.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-31T00:00:00"}