{"id":"https://openalex.org/W4408356038","doi":"https://doi.org/10.1109/icassp49660.2025.10890322","title":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis","display_name":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356038","doi":"https://doi.org/10.1109/icassp49660.2025.10890322"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000060266","display_name":"Jaemin Jung","orcid":"https://orcid.org/0000-0002-6815-7763"},"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":"Jaemin Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101355949","display_name":"Junseok Ahn","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":"Junseok Ahn","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062754007","display_name":"Chaeyoung Jung","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":"Chaeyoung Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111922287","display_name":"Tan Dat Nguyen","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":"Tan Dat Nguyen","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"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":"Youngjoon Jang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South 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,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000060266"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95791921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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":0.9944000244140625,"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":0.9891999959945679,"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/T12031","display_name":"Speech and dialogue systems","score":0.9315000176429749,"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/computer-science","display_name":"Computer science","score":0.6345453262329102},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.527490496635437},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5170191526412964},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5030228495597839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43731093406677246},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2943296730518341},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12335023283958435},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08519360423088074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345453262329102},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.527490496635437},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5170191526412964},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5030228495597839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43731093406677246},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2943296730518341},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12335023283958435},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08519360423088074},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":46,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2972359262","https://openalex.org/W3209984917","https://openalex.org/W4312933868","https://openalex.org/W4367359628","https://openalex.org/W4372260220","https://openalex.org/W4372260365","https://openalex.org/W4372348103","https://openalex.org/W4385570943","https://openalex.org/W4385823191","https://openalex.org/W4390872297","https://openalex.org/W4392902843","https://openalex.org/W4392903890","https://openalex.org/W4392904136","https://openalex.org/W4393160294","https://openalex.org/W4396877837","https://openalex.org/W4400033239","https://openalex.org/W4402111799","https://openalex.org/W4403674737","https://openalex.org/W4411245083","https://openalex.org/W6757220786","https://openalex.org/W6757817989","https://openalex.org/W6771467084","https://openalex.org/W6776048684","https://openalex.org/W6777694618","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6791353385","https://openalex.org/W6795261426","https://openalex.org/W6845479124","https://openalex.org/W6846849257","https://openalex.org/W6847363464","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849953009","https://openalex.org/W6852240503","https://openalex.org/W6856434366","https://openalex.org/W6856607740","https://openalex.org/W6859583170","https://openalex.org/W6861353174","https://openalex.org/W6862144568","https://openalex.org/W6869001559","https://openalex.org/W6869691399"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0],"present":[1,47],"VoiceDiT,":[2],"a":[3,35,48,65,73,83,99],"multi-modal":[4,125],"generative":[5],"model":[6,84,106],"for":[7,25,70,78],"producing":[8],"environment-aware":[9],"speech":[10,20,68,76,90],"and":[11,15,37,72,97,113,146],"audio":[12,50,112,144],"from":[13],"text":[14,22],"visual":[16],"prompts.":[17,126],"While":[18],"aligning":[19],"with":[21,123],"is":[23],"crucial":[24],"intelligible":[26],"speech,":[27],"achieving":[28],"this":[29],"alignment":[30],"in":[31,40,142],"noisy":[32],"conditions":[33],"remains":[34],"significant":[36,140],"underexplored":[38],"challenge":[39],"the":[41,62,81,105,109,116,124],"field.":[42],"To":[43],"address":[44],"this,":[45],"we":[46],"novel":[49],"generation":[51,117],"pipeline":[52,56],"named":[53],"VoiceDiT.":[54],"This":[55],"includes":[57],"three":[58],"key":[59],"components:":[60],"(1)":[61],"creation":[63],"of":[64,118],"large-scale":[66],"synthetic":[67],"dataset":[69,77],"pre-training":[71],"refined":[74],"real-world":[75,137],"fine-tuning,":[79],"(2)":[80],"Dual-DiT,":[82],"designed":[85],"to":[86,107],"efficiently":[87],"preserve":[88],"aligned":[89],"information":[91],"while":[92],"accurately":[93],"reflecting":[94],"environmental":[95,119],"conditions,":[96],"(3)":[98],"diffusion-based":[100],"Image-to-Audio":[101],"Translator":[102],"that":[103,121,131],"allows":[104],"bridge":[108],"gap":[110],"between":[111],"image,":[114],"facilitating":[115],"sound":[120],"aligns":[122],"Extensive":[127],"experimental":[128],"results":[129],"demonstrate":[130],"VoiceDiT":[132],"outperforms":[133],"previous":[134],"models":[135],"on":[136,153],"datasets,":[138],"showcasing":[139],"improvements":[141],"both":[143],"quality":[145],"modality":[147],"integration.":[148],"Synthesized":[149],"samples":[150],"are":[151],"available":[152],"our":[154],"demo":[155],"page:":[156],"https://mm.kaist.ac.kr/projects/voicedit/":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}