{"id":"https://openalex.org/W7166807490","doi":"https://doi.org/10.18653/v1/2026.acl-long.1774","title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","display_name":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166807490","doi":"https://doi.org/10.18653/v1/2026.acl-long.1774"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1774","doi":"https://doi.org/10.18653/v1/2026.acl-long.1774","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1774","pdf_url":"https://aclanthology.org/2026.acl-long.1774.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1774.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137597457","display_name":"Jun-Hak Yun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Hak Yun","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University , Seoul , Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139729017","display_name":"Seung-Bin Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University , Seoul , Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139759873","display_name":"Seong-Whan Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University , Seoul , Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43510962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38295","last_page":"38314"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":9.999999747378752e-05,"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":[{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5364000201225281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29919999837875366},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.24150000512599945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23600000143051147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1774","doi":"https://doi.org/10.18653/v1/2026.acl-long.1774","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1774","pdf_url":"https://aclanthology.org/2026.acl-long.1774.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1774","doi":"https://doi.org/10.18653/v1/2026.acl-long.1774","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1774","pdf_url":"https://aclanthology.org/2026.acl-long.1774.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6969530878","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G8458676037","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G960095468","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166807490.pdf","grobid_xml":"https://content.openalex.org/works/W7166807490.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417308863","https://openalex.org/W4408356038","https://openalex.org/W4417081749","https://openalex.org/W4392902843","https://openalex.org/W7172538943","https://openalex.org/W3205925339","https://openalex.org/W4408352615","https://openalex.org/W4402118926","https://openalex.org/W4416798814","https://openalex.org/W7202375521"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,10,32],"text-guided":[3],"audio":[4,24,100,111],"generation":[5],"have":[6],"yielded":[7],"promising":[8],"results":[9,102],"diverse":[11],"domains,":[12],"including":[13],"sound":[14],"effects,":[15],"speech,":[16],"and":[17,36,67,99,110,119],"music.However,":[18],"jointly":[19],"generating":[20],"speech":[21,49,70,98],"with":[22,72],"environmental":[23,53,74],"remains":[25],"challenging":[26],"due":[27],"to":[28,90],"the":[29],"inherent":[30],"disparities":[31],"their":[33],"acoustic":[34],"patterns":[35],"temporal":[37],"dynamics.We":[38],"propose":[39],"ImmersiveTTS,":[40],"an":[41],"environment-aware":[42],"text-to-speech":[43],"(TTS)":[44],"model":[45,60],"that":[46,104],"generates":[47],"natural":[48],"seamlessly":[50],"integrated":[51],"within":[52],"contexts":[54],"by":[55],"explicitly":[56],"modeling":[57],"cross-modal":[58],"interactions.Our":[59],"builds":[61],"on":[62],"a":[63,84],"multimodal":[64],"diffusion":[65],"transformer":[66],"fuses":[68],"transcript-aligned":[69],"latent":[71],"textconditioned":[73],"context":[75],"via":[76],"joint":[77],"attention.To":[78],"enhance":[79],"semantic":[80],"consistency,":[81],"we":[82],"introduce":[83],"domain-specific":[85],"representation":[86],"alignment":[87],"objective":[88,117],"tailored":[89],"environmentaware":[91],"TTS,":[92],"leveraging":[93],"complementary":[94],"selfsupervised":[95],"representations":[96],"from":[97],"encoders.Experimental":[101],"show":[103],"ImmersiveTTS":[105],"achieves":[106],"higher":[107],"naturalness,":[108],"intelligibility,":[109],"fidelity":[112],"than":[113],"existing":[114],"approaches":[115],"across":[116],"metrics":[118],"human":[120],"listening":[121],"tests.":[122]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}