{"id":"https://openalex.org/W7225833541","doi":"https://doi.org/10.48550/arxiv.2611.13875","title":"DialInstruct-TTS: Interactive Expressive Speech Generation via Multi-Turn Dialogue with Fine-Grained Temporal Control","display_name":"DialInstruct-TTS: Interactive Expressive Speech Generation via Multi-Turn Dialogue with Fine-Grained Temporal Control","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225833541","doi":"https://doi.org/10.48550/arxiv.2611.13875"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.13875","doi":"https://doi.org/10.48550/arxiv.2611.13875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13875","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.13875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126292799","display_name":"Wangzixi Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wangzixi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824","observed_orcids":["https://orcid.org/0000-0003-1560-2824"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atmaja, Bagus Tris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963","observed_orcids":["https://orcid.org/0000-0001-5509-8963"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakti, Sakriani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0032999999821186066,"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/T10860","display_name":"Speech and Audio Processing","score":0.000699999975040555,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7893000245094299},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C2779760435","wikidata":"https://www.wikidata.org/wiki/Q5396169","display_name":"Minor (academic)","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.13875","doi":"https://doi.org/10.48550/arxiv.2611.13875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13875","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.13875","doi":"https://doi.org/10.48550/arxiv.2611.13875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13875","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"instruction-based":[1],"TTS":[2,47],"systems":[3],"primarily":[4],"support":[5],"one-shot,":[6],"utterance-level":[7],"control,":[8],"where":[9],"a":[10,22,70,82,86],"single":[11],"instruction":[12,30,80,129,146],"determines":[13],"the":[14,29,33,61,74,113],"speaking":[15,96],"style":[16,63,133],"of":[17],"an":[18,43],"entire":[19],"utterance.":[20],"As":[21],"result,":[23],"even":[24],"minor":[25],"refinements":[26],"require":[27],"rewriting":[28],"and":[31,77,99,135,148,156],"regenerating":[32],"full":[34,145],"utterance,":[35],"limiting":[36],"fine-grained":[37,92],"interactive":[38,44],"control.":[39],"We":[40],"propose":[41],"DialInstruct-TTS,":[42],"multi-turn":[45],"expressive":[46],"framework":[48],"that":[49],"enables":[50],"users":[51,109],"to":[52,110],"iteratively":[53],"refine":[54],"generated":[55],"speech":[56],"through":[57],"natural-language":[58],"dialogue":[59,68,75],"until":[60],"desired":[62],"is":[64],"achieved.":[65],"At":[66],"each":[67],"turn,":[69],"Qwen-based":[71],"planner":[72],"integrates":[73],"history":[76],"latest":[78],"user":[79],"into":[81],"complete":[83],"TemporalPlan,":[84],"while":[85,119],"temporal":[87,117],"acoustic":[88],"control":[89,93],"module":[90],"provides":[91],"over":[94],"emotion,":[95],"rate,":[97],"volume,":[98],"phonation.":[100],"Reference-latent":[101],"revision":[102],"preserves":[103],"non-target":[104,137],"regions":[105],"across":[106],"turns,":[107],"allowing":[108],"modify":[111],"only":[112],"requested":[114],"attributes":[115],"or":[116],"spans":[118],"retaining":[120],"previously":[121],"satisfactory":[122],"speech.":[123],"Subjective":[124],"evaluations":[125],"demonstrate":[126],"improved":[127],"global":[128],"following,":[130],"accurate":[131],"local":[132],"realization,":[134],"effective":[136],"preservation.":[138],"Compared":[139],"with":[140],"conventional":[141],"one-shot":[142],"interaction":[143,157],"requiring":[144],"restatement":[147],"utterance":[149],"regeneration,":[150],"DialInstruct-TTS":[151],"substantially":[152],"improves":[153],"perceived":[154],"convenience":[155],"comfort.":[158],"Audio":[159],"samples":[160],"are":[161],"available":[162],"at":[163],"https://anonymous.4open.science/w/eacl-demo-17C5/.":[164]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
