{"id":"https://openalex.org/W4415707820","doi":"https://doi.org/10.1109/icme59968.2025.11209338","title":"DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue","display_name":"DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707820","doi":"https://doi.org/10.1109/icme59968.2025.11209338"},"language":"en","primary_location":{"id":"doi:10.1109/icme59968.2025.11209338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5091948790","display_name":"Xiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057801749","display_name":"Dongteng Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Duyi Pan","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053229311","display_name":"Hongru Xiao","orcid":"https://orcid.org/0009-0007-6715-357X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongru Xiao","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011412438","display_name":"Jiale Han","orcid":"https://orcid.org/0000-0001-6477-0424"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiale Han","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451926","display_name":"Jing Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Tang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321032","display_name":"Xinhua Ma","orcid":"https://orcid.org/0000-0002-6277-0292"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Jiabao Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391888","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1568-2396"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100640942","display_name":"Bo Cheng","orcid":"https://orcid.org/0000-0003-2160-2839"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Bo Cheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5091948790"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17503204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10028","display_name":"Topic Modeling","score":0.45579999685287476,"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/T10028","display_name":"Topic Modeling","score":0.45579999685287476,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.19740000367164612,"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":0.11330000311136246,"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/paralanguage","display_name":"Paralanguage","score":0.8019000291824341},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6525999903678894},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6043000221252441},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5910999774932861},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5516999959945679},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35850000381469727},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8019000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962999939918518},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5006999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4043999910354614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2563999891281128}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11209338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167112","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167112","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2964243274","https://openalex.org/W4225956675","https://openalex.org/W4372260474","https://openalex.org/W4385822427","https://openalex.org/W4402111455","https://openalex.org/W4402671543","https://openalex.org/W4402672034","https://openalex.org/W4404782209"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,46,140],"is":[2],"crucial":[3],"for":[4],"human-computer":[5],"interaction,":[6],"enabling":[7],"natural":[8],"and":[9,23,31,58,77,87,117,129,142],"intuitive":[10],"communication.":[11],"However,":[12],"existing":[13],"datasets":[14],"involve":[15],"high":[16,119],"construction":[17],"costs":[18],"due":[19],"to":[20,133],"manual":[21],"annotation":[22],"suffer":[24],"from":[25],"limited":[26],"character":[27,69],"diversity,":[28],"contextual":[29],"scenarios,":[30],"emotional":[32,85],"expressiveness.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"we":[38,96],"propose":[39],"DialogueAgents,":[40],"a":[41,55,59,67,99],"novel":[42],"hybrid":[43],"agent-based":[44],"speech":[45,56,79,82,103,139],"framework,":[47],"which":[48],"integrates":[49],"three":[50],"specialized":[51],"agents\u2014a":[52],"script":[53],"writer,":[54],"synthesizer,":[57],"dialogue":[60,75,104],"critic\u2014to":[61],"collaboratively":[62],"generate":[63],"dialogues.":[64,93],"Grounded":[65],"in":[66],"diverse":[68,107],"pool,":[70],"the":[71,91,112,118,122,127],"framework":[72,116],"iteratively":[73],"refines":[74],"scripts":[76],"synthesizes":[78],"based":[80],"on":[81,137],"review,":[83],"boosting":[84],"expressiveness":[86],"paralinguistic":[88],"features":[89],"of":[90,114,121],"synthesized":[92],"Using":[94],"DialogueAgent,":[95],"contribute":[97],"MultiTalk,":[98],"bilingual,":[100],"multi-party,":[101],"multi-turn":[102],"dataset":[105,128],"covering":[106],"topics.":[108],"Extensive":[109],"experiments":[110],"demonstrate":[111],"effectiveness":[113],"our":[115],"quality":[120],"MultiTalk":[123],"dataset.":[124],"We":[125],"release":[126],"code<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[132],"facilitate":[134],"future":[135],"research":[136],"advanced":[138],"models":[141],"customized":[143],"data":[144],"generation.":[145]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}
