{"id":"https://openalex.org/W4416036598","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.448","title":"Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis","display_name":"Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036598","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.448"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.448","pdf_url":"https://aclanthology.org/2025.emnlp-main.448.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.448.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113419937","display_name":"Zhenqi Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhenqi Jia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448456","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-2967-6296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113419937"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5953,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92449226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8863","last_page":"8869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.41929998993873596,"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/T12031","display_name":"Speech and dialogue systems","score":0.41929998993873596,"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":0.26510000228881836,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.09950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5069000124931335},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.40799999237060547},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.37119999527931213},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.32109999656677246},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.26460000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037000060081482},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43970000743865967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.448","pdf_url":"https://aclanthology.org/2025.emnlp-main.448.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.448","pdf_url":"https://aclanthology.org/2025.emnlp-main.448.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1023919524","display_name":null,"funder_award_id":", Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4843415936","display_name":"Instantons, Lagrangians, and Low Dimensional Topology","funder_award_id":"2208181","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G600008135","display_name":null,"funder_award_id":"62206136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6755165505","display_name":null,"funder_award_id":"award","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6801188043","display_name":"CAREER: What is in a Voice?: Scientific and Machine Learning Advancement for Voice Conversion","funder_award_id":"2338979","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G714025552","display_name":"Computer Science, Engineering and Mathematics Scholarships Project","funder_award_id":"0220818","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8714109953","display_name":null,"funder_award_id":"QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036598.pdf","grobid_xml":"https://content.openalex.org/works/W4416036598.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conversational":[0],"Speech":[1],"Synthesis":[2],"(CSS)":[3],"aims":[4],"to":[5,118],"generate":[6],"speech":[7,121,143],"with":[8,122],"natural":[9,123],"prosody":[10,23,46,91],"by":[11,29],"understanding":[12],"the":[13,21,26,31,38,49,54,127],"multimodal":[14,80],"dialogue":[15,82],"history":[16],"(MDH).The":[17],"latest":[18],"work":[19],"predicts":[20],"accurate":[22],"expression":[24],"of":[25,35,139],"target":[27,39],"utterance":[28],"modeling":[30],"utterance-level":[32],"interaction":[33,59,83,87,92,95,113],"characteristics":[34],"MDH":[36,41],"and":[37,45,57,89,104,142],"utterance.However,":[40],"contains":[42],"fine-grained":[43,55,81],"semantic":[44,56,86],"knowledge":[47],"at":[48,147],"word":[50],"level.Existing":[51],"methods":[52],"overlook":[53],"prosodic":[58,140],"modeling.To":[60],"address":[61],"this":[62],"gap,":[63],"we":[64],"propose":[65],"MFCIG-CSS,":[66],"a":[67,85,90],"novel":[68],"Multimodal":[69],"Fine-grained":[70],"Context":[71],"Interaction":[72],"Graph-based":[73],"CSS":[74],"system.Our":[75],"approach":[76],"constructs":[77],"two":[78,94],"specialized":[79],"graphs:":[84],"graph":[88],"graph.These":[93],"graphs":[96],"effectively":[97],"encode":[98],"interactions":[99],"between":[100],"word-level":[101],"semantics,":[102],"prosody,":[103],"their":[105],"influence":[106],"on":[107,126],"subsequent":[108],"utterances":[109],"in":[110,137],"MDH.The":[111],"encoded":[112],"features":[114],"are":[115,145],"then":[116],"leveraged":[117],"enhance":[119],"synthesized":[120],"conversational":[124],"prosody.Experiments":[125],"DailyTalk":[128],"dataset":[129],"demonstrate":[130],"that":[131],"MFCIG-CSS":[132],"outperforms":[133],"all":[134],"baseline":[135],"models":[136],"terms":[138],"expressiveness.Code":[141],"samples":[144],"available":[146],"https://github.com/AI-S2-Lab/MFCIG-CSS.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-11-08T00:00:00"}