{"id":"https://openalex.org/W4408353042","doi":"https://doi.org/10.1109/icassp49660.2025.10889780","title":"V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow","display_name":"V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353042","doi":"https://doi.org/10.1109/icassp49660.2025.10889780"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889780","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/A5111556720","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0000-0002-5554-3657"},"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"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377806","display_name":"Jihoon Kim","orcid":"https://orcid.org/0000-0002-6391-8711"},"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"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365066","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0003-3045-6220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Mircrosoft"],"affiliations":[{"raw_affiliation_string":"Mircrosoft","institution_ids":[]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115590404","display_name":"Shujie Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Mircrosoft"],"affiliations":[{"raw_affiliation_string":"Mircrosoft","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111556720"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.053091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.964900016784668,"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":0.949999988079071,"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/speech-recognition","display_name":"Speech recognition","score":0.7120444774627686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6914336681365967},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4736969470977783},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.43137669563293457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34193283319473267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10672721266746521}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7120444774627686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914336681365967},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4736969470977783},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.43137669563293457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34193283319473267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10672721266746521},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889780","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":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2604379605","https://openalex.org/W2625027024","https://openalex.org/W2752796333","https://openalex.org/W2949662773","https://openalex.org/W2962788625","https://openalex.org/W2963936489","https://openalex.org/W3034552680","https://openalex.org/W3081492798","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3141523618","https://openalex.org/W3157840621","https://openalex.org/W3162293946","https://openalex.org/W3163296124","https://openalex.org/W3209059054","https://openalex.org/W3216976702","https://openalex.org/W4224319127","https://openalex.org/W4225956675","https://openalex.org/W4283809657","https://openalex.org/W4294435344","https://openalex.org/W4296069328","https://openalex.org/W4375868850","https://openalex.org/W4385574033","https://openalex.org/W4385823403","https://openalex.org/W4386076005","https://openalex.org/W4387969537","https://openalex.org/W4390872297","https://openalex.org/W4390872449","https://openalex.org/W4393156644","https://openalex.org/W4393158256","https://openalex.org/W4401607735","https://openalex.org/W4402112495","https://openalex.org/W4402671671","https://openalex.org/W6739901393","https://openalex.org/W6754420807","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6803359641","https://openalex.org/W6803547063","https://openalex.org/W6810168380","https://openalex.org/W6840815571","https://openalex.org/W6843731886","https://openalex.org/W6853966563","https://openalex.org/W6862995742"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3,62,98],"introduce":[4],"V2SFlow,":[5],"a":[6,100,107],"novel":[7],"Video-to-Speech":[8],"(V2S)":[9],"framework":[10],"designed":[11],"to":[12,49,118],"generate":[13,89],"natural":[14],"and":[15,38,53,72,80,91],"intelligible":[16],"speech":[17,56,65,78,93,121],"directly":[18,83],"from":[19,84,94,115],"silent":[20],"talking":[21],"face":[22],"videos.":[23],"While":[24],"recent":[25],"V2S":[26],"systems":[27],"have":[28],"shown":[29],"promising":[30],"results":[31],"on":[32,44,106],"constrained":[33],"datasets":[34,47],"with":[35],"limited":[36],"speakers":[37],"vocabularies,":[39],"their":[40],"performance":[41],"often":[42],"degrades":[43],"real-world,":[45],"unconstrained":[46],"due":[48],"the":[50,64,85,119,134],"inherent":[51],"variability":[52],"complexity":[54],"of":[55,136],"signals.":[57],"To":[58,88],"address":[59],"these":[60,95],"challenges,":[61],"decompose":[63],"signal":[66],"into":[67],"manageable":[68],"subspaces":[69],"(content,":[70],"pitch,":[71],"speaker":[73],"information),":[74],"each":[75],"representing":[76],"distinct":[77],"attributes,":[79,97],"predict":[81],"them":[82],"visual":[86],"input.":[87],"coherent":[90],"realistic":[92],"predicted":[96],"employ":[99],"rectified":[101],"flow":[102],"matching":[103],"decoder":[104],"built":[105],"Transformer":[108],"architecture,":[109],"which":[110],"models":[111],"efficient":[112],"probabilistic":[113],"pathways":[114],"random":[116],"noise":[117],"target":[120],"distribution.":[122],"Extensive":[123],"experiments":[124],"demonstrate":[125],"that":[126],"V2SFlow":[127],"significantly":[128],"outperforms":[129],"state-of-the-art":[130],"methods,":[131],"even":[132],"surpassing":[133],"naturalness":[135],"ground":[137],"truth":[138],"utterances.":[139]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}