{"id":"https://openalex.org/W4387968649","doi":"https://doi.org/10.1145/3581783.3613823","title":"Emotionally Situated Text-to-Speech Synthesis in User-Agent Conversation","display_name":"Emotionally Situated Text-to-Speech Synthesis in User-Agent Conversation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968649","doi":"https://doi.org/10.1145/3581783.3613823"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5089692739","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0002-6873-7530"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6873-7530","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102867715","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0009-0008-9646-9802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["ByteDance, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-9646-9802","affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020416379","display_name":"Shichao Liu","orcid":"https://orcid.org/0009-0008-7218-3877"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichao Liu","raw_affiliation_strings":["Bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7218-3877","affiliations":[{"raw_affiliation_string":"Bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102916605","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0472-2783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Bytedance, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0472-2783","affiliations":[{"raw_affiliation_string":"Bytedance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023494011","display_name":"Zejun Ma","orcid":"https://orcid.org/0000-0001-5508-1328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5508-1328","affiliations":[{"raw_affiliation_string":"Bytedance, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6486-6020","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089692739"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":1.0225,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81560663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5966","last_page":"5974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/conversation","display_name":"Conversation","score":0.887237548828125},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.7981117963790894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963979244232178},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6493982076644897},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6194303631782532},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5026893615722656},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49759677052497864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4838925302028656},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45807620882987976},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.45250993967056274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32284218072891235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2745819091796875},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2119370698928833},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.0902131199836731}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.887237548828125},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.7981117963790894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963979244232178},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6493982076644897},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6194303631782532},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5026893615722656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49759677052497864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4838925302028656},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45807620882987976},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.45250993967056274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32284218072891235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2745819091796875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2119370698928833},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.0902131199836731},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G8390650537","display_name":null,"funder_award_id":"62072462","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2740887992","https://openalex.org/W2964243274","https://openalex.org/W2964300796","https://openalex.org/W2964309167","https://openalex.org/W2998563994","https://openalex.org/W3010916717","https://openalex.org/W3092028330","https://openalex.org/W3151309757","https://openalex.org/W4255717863","https://openalex.org/W4304013787","https://openalex.org/W4387872955"],"related_works":["https://openalex.org/W1600697036","https://openalex.org/W1601337804","https://openalex.org/W4392983437","https://openalex.org/W2035858348","https://openalex.org/W2155106162","https://openalex.org/W2010047220","https://openalex.org/W2004235806","https://openalex.org/W2806021742","https://openalex.org/W1929025370","https://openalex.org/W3156017614"],"abstract_inverted_index":{"Conversational":[0],"Text-to-speech":[1,85],"Synthesis":[2,86],"(TTS)":[3],"aims":[4],"to":[5,28,89],"generate":[6,98],"speech":[7,99],"with":[8,100],"proper":[9,71,101],"style":[10,30,103],"in":[11,24,39,73,107,129],"the":[12,22,25,33,41,49,53,56,74,108,113,117,124],"user-agent":[13,109,125],"conversation":[14],"scenario.":[15],"Although":[16],"previous":[17,46],"works":[18,47],"have":[19],"explored":[20],"modeling":[21,40],"context":[23],"dialogue":[26],"history":[27],"provide":[29],"information":[31],"for":[32,123],"agent,":[34,57],"there":[35],"are":[36,148],"still":[37],"deficiencies":[38],"role-aware":[42],"multi-modal":[43],"context.":[44],"Moreover,":[45],"ignore":[48],"emotional":[50,63,95,105],"dependencies":[51],"between":[52],"user":[54],"and":[55,67,93,97,104],"which":[58,134],"includes:":[59],"1)":[60],"agent":[61,69],"understands":[62],"states":[64],"of":[65,119,131,144],"users,":[66],"2)":[68],"expresses":[70],"emotion":[72],"generated":[75],"speech.":[76],"In":[77],"this":[78],"work,":[79],"we":[80],"propose":[81],"an":[82],"Emotionally":[83],"Situated":[84],"(EmoSit-TTS)":[87],"framework":[88,122,147],"understand":[90],"users'":[91],"semantics":[92],"subtle":[94],"states,":[96],"speaking":[102],"expression":[106],"conversation.":[110],"Experiments":[111],"on":[112,141],"DailyTalk":[114],"dataset":[115],"show":[116],"superiority":[118],"our":[120,145],"proposed":[121,146],"conversational":[126],"TTS,":[127],"especially":[128],"terms":[130],"emotion-aware":[132],"expressiveness,":[133],"outperforms":[135],"other":[136],"state-of-the-art":[137],"methods":[138],"by":[139],"0.69":[140],"MOS.":[142],"Demos":[143],"available":[149],"at":[150],"https://anonydemo.github.io.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}