{"id":"https://openalex.org/W4416799683","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249327","title":"Dialospeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching","display_name":"Dialospeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799683","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249327"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5076493382","display_name":"Hanke Xie","orcid":"https://orcid.org/0009-0000-5318-8092"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanke Xie","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377824","display_name":"Dake Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dake Guo","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015144801","display_name":"Chengyou Wang","orcid":"https://orcid.org/0000-0002-0901-2492"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyou Wang","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387803","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-5624-7235"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111283523","display_name":"Wenjie Tian","orcid":"https://orcid.org/0009-0000-3211-3219"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Tian","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748253","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0001-5338-8166"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562197","display_name":"Xiulin Li","orcid":"https://orcid.org/0000-0003-3581-2968"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulin Li","raw_affiliation_strings":["DataBaker (Qingdao) Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DataBaker (Qingdao) Technology","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002880112","display_name":"Guanqiong Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanqiong Miao","raw_affiliation_strings":["DataBaker (Qingdao) Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DataBaker (Qingdao) Technology","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461621","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-0894-1054"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["DataBaker (Qingdao) Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DataBaker (Qingdao) Technology","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036533907","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-4039-2411"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASLP, Northwestern Polytechnical University,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17659665,"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":0.40880000591278076,"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":0.40880000591278076,"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":0.25929999351501465,"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":0.17190000414848328,"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/construct","display_name":"Construct (python library)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6620000004768372},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5648999810218811},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49630001187324524},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.46970000863075256},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4462999999523163},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39419999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263999819755554},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6620000004768372},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5595999956130981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.46970000863075256},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4462999999523163},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2963308316","https://openalex.org/W3024869864","https://openalex.org/W3209059054","https://openalex.org/W4225302959","https://openalex.org/W4283067311","https://openalex.org/W4307680525","https://openalex.org/W4391621214","https://openalex.org/W4412945617"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,40,56],"text-to-speech":[3],"(TTS)":[4],"synthesis,":[5],"particularly":[6],"those":[7],"leveraging":[8],"large":[9,80],"language":[10,81],"models":[11],"(LLMs),":[12],"have":[13],"significantly":[14],"improved":[15],"expressiveness":[16],"and":[17,38,45,53,69,102,108,110,128],"naturalness.":[18],"However,":[19],"generating":[20,142],"human-like,":[21],"interactive":[22],"dialogue":[23,90,123],"speech":[24,91,112],"remains":[25],"challenging.":[26],"Current":[27],"systems":[28],"face":[29],"limitations":[30],"due":[31],"to":[32,120],"the":[33],"scarcity":[34],"of":[35],"dual-track":[36,76,122],"data":[37,117],"difficulties":[39],"achieving":[41],"naturalness,":[42],"contextual":[43],"coherence,":[44],"interactional":[46],"dynamics,":[47],"such":[48],"as":[49],"turntaking,":[50],"overlapping":[51],"speech,":[52],"speaker":[54,100],"consistency,":[55],"multiturn":[57],"conversations.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"propose":[64],"DialoSpeech":[65,93],"<sup":[66],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>1Codes":[68],"checkpoints":[70],"will":[71],"be":[72],"publicly":[73],"released.,":[74],"a":[75,79,116,139],"architecture":[77],"combining":[78],"model":[82,135],"with":[83,98],"Chunked":[84],"Flow":[85],"Matching":[86],"for":[87,141],"expressive,":[88],"humanlike":[89],"synthesis.":[92,113],"generates":[94],"natural":[95,103],"multi-turn":[96],"conversations":[97],"coherent":[99],"turns":[101],"overlaps,":[104],"supporting":[105],"both":[106],"Chinese":[107],"English":[109],"crosslingual":[111],"We":[114],"introduce":[115],"processing":[118],"pipeline":[119],"construct":[121],"datasets,":[124],"facilitating":[125],"scalable":[126],"training":[127],"experimental":[129],"validation.":[130],"Experiments":[131],"show":[132],"that":[133],"our":[134],"outperforms":[136],"baselines,":[137],"offering":[138],"solution":[140],"human-like":[143],"spoken":[144],"dialogues.":[145],"Audio":[146],"samples":[147],"are":[148],"available":[149],"at":[150],"https://tiamojames.github.io/DialoSpeech/":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}