{"id":"https://openalex.org/W4415536718","doi":"https://doi.org/10.1145/3746027.3754577","title":"AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation","display_name":"AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536718","doi":"https://doi.org/10.1145/3746027.3754577"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754577","pdf_url":null,"source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754577","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101725649","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0009-0005-6817-604X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-6817-604X","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108125215","display_name":"Ji-Hoon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji-Hoon Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-3433-918X","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041045917","display_name":"Kim Sung-Bin","orcid":"https://orcid.org/0000-0003-3542-9934"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim Sung-Bin","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3542-9934","affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0468-1571","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101725649"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.9153,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89925783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"10758","last_page":"10767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9973000288009644,"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":0.9853000044822693,"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/transformer","display_name":"Transformer","score":0.6485000252723694},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41600000858306885},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.38909998536109924},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.388700008392334},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34290000796318054},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.34150001406669617},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6485000252723694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754577","pdf_url":null,"source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754577","pdf_url":null,"source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W3097777922","https://openalex.org/W4385823403","https://openalex.org/W4402683936"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,73,112],"address":[4,70],"the":[5,66,94,99,122],"task":[6,26],"of":[7,36,98,148],"multimodal-to-speech":[8],"generation,":[9],"which":[10],"aims":[11],"to":[12,32,65,107,124],"synthesize":[13],"high-quality":[14],"speech":[15,56,60,87,132],"from":[16,53,88,128],"multiple":[17,144],"input":[18],"modalities:":[19],"text,":[20],"video,":[21],"and":[22,43,62,85,151,168],"reference":[23,67],"audio.":[24],"This":[25],"has":[27],"gained":[28],"increasing":[29],"attention":[30],"due":[31],"its":[33],"wide":[34],"range":[35],"applications,":[37],"such":[38,164],"as":[39,165],"film":[40],"production,":[41],"dubbing,":[42],"virtual":[44],"avatars.":[45],"Despite":[46],"recent":[47],"progress,":[48],"existing":[49,141],"methods":[50,142],"still":[51],"suffer":[52],"limitations":[54],"in":[55,146],"intelligibility,":[57],"audio-video":[58],"synchronization,":[59,150],"naturalness,":[61],"voice":[63],"similarity":[64],"speaker.":[68],"To":[69],"these":[71],"challenges,":[72],"propose":[74],"AlignDiT,":[75],"a":[76,114],"multimodal":[77,90,109,116,162],"Aligned":[78],"Diffusion":[79],"Transformer":[80],"that":[81,120,137],"generates":[82],"accurate,":[83],"synchronized,":[84],"natural-sounding":[86],"aligned":[89],"inputs.":[91],"Built":[92],"upon":[93],"in-context":[95],"learning":[96],"capability":[97,159],"DiT":[100],"architecture,":[101],"AlignDiT":[102,138,155],"explores":[103],"three":[104],"effective":[105],"strategies":[106],"align":[108],"representations.":[110],"Furthermore,":[111],"introduce":[113],"novel":[115],"classifier-free":[117],"guidance":[118],"mechanism":[119],"allows":[121],"model":[123],"adaptively":[125],"balance":[126],"information":[127],"each":[129],"modality":[130],"during":[131],"synthesis.":[133],"Extensive":[134],"experiments":[135],"demonstrate":[136],"significantly":[139],"outperforms":[140],"across":[143,160],"benchmarks":[145],"terms":[147],"quality,":[149],"speaker":[152],"similarity.":[153],"Moreover,":[154],"exhibits":[156],"strong":[157],"generalization":[158],"various":[161],"tasks,":[163],"video-to-speech":[166],"synthesis":[167],"visual":[169],"forced":[170],"alignment,":[171],"consistently":[172],"achieving":[173],"state-of-the-art":[174],"performance.":[175],"The":[176],"demo":[177],"page":[178],"is":[179],"available":[180],"at":[181],"https://mm.kaist.ac.kr/projects/AlignDiT.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-25T00:00:00"}
