{"id":"https://openalex.org/W4392931031","doi":"https://doi.org/10.1109/icassp48485.2024.10447679","title":"Seeing Through The Conversation: Audio-Visual Speech Separation Based on Diffusion Model","display_name":"Seeing Through The Conversation: Audio-Visual Speech Separation Based on Diffusion Model","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931031","doi":"https://doi.org/10.1109/icassp48485.2024.10447679"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100649773","display_name":"Suyeon Lee","orcid":"https://orcid.org/0000-0002-1468-3768"},"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":"Suyeon Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","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"]},{"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","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"]},{"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","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"]},{"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/A5101733121","display_name":"Jaehun Kim","orcid":"https://orcid.org/0000-0002-3200-0406"},"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":"Jaehun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","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"]},{"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","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"]},{"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":5,"corresponding_author_ids":["https://openalex.org/A5100649773"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":3.3624,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9285298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12632","last_page":"12636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9108978509902954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242937326431274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6349136829376221},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6095690727233887},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5708211064338684},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.509589672088623},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4663267433643341},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4646989703178406},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4394943118095398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4209742844104767},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4117870628833771},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15302225947380066}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9108978509902954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242937326431274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6349136829376221},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6095690727233887},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5708211064338684},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.509589672088623},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4663267433643341},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4646989703178406},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4394943118095398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4209742844104767},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4117870628833771},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15302225947380066},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5299999713897705,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8472331835","display_name":null,"funder_award_id":"2022-0-00989","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2013035813","https://openalex.org/W2015394094","https://openalex.org/W2170316986","https://openalex.org/W2516001803","https://openalex.org/W2808631503","https://openalex.org/W2891205112","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2973231102","https://openalex.org/W3016011581","https://openalex.org/W3182657421","https://openalex.org/W3213412873","https://openalex.org/W4289665794","https://openalex.org/W4312337341","https://openalex.org/W4312933868","https://openalex.org/W4313048484","https://openalex.org/W4372341629","https://openalex.org/W4375869052","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W6631190155","https://openalex.org/W6679045638","https://openalex.org/W6754420807","https://openalex.org/W6765775151","https://openalex.org/W6778946027","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6798523648"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2549308614"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,15,75,112],"this":[3,40,102],"work":[4],"is":[5,83],"to":[6,59,90],"extract":[7],"the":[8,76,87,92,104,108,113,122],"target":[9],"speaker\u2019s":[10],"voice":[11],"from":[12,95],"a":[13,52,66],"mixture":[14],"voices":[16],"using":[17],"visual":[18],"cues.":[19],"Existing":[20],"works":[21],"on":[22,51,128],"audio-visual":[23,46,96],"speech":[24,47,88,99,136],"separation":[25,48],"have":[26],"demonstrated":[27],"their":[28],"performance":[29],"with":[30,137,143],"promising":[31],"intelligibility,":[32],"but":[33],"maintaining":[34],"naturalness":[35],"remains":[36],"challenging.":[37],"To":[38],"address":[39],"issue,":[41],"we":[42],"propose":[43,65],"AVDiffuSS,":[44],"an":[45,72],"model":[49],"based":[50],"diffusion":[53],"mechanism":[54,70,82],"known":[55],"for":[56,71,79,86],"its":[57],"capability":[58],"generate":[60],"natural":[61],"samples.":[62],"We":[63,119],"also":[64],"cross-attention-based":[67],"feature":[68],"fusion":[69,74,105],"effective":[73],"two":[77,129],"modalities":[78],"diffusion.":[80],"This":[81],"specifically":[84],"tailored":[85],"domain":[89],"integrate":[91],"phonetic":[93],"information":[94],"correspondence":[97],"in":[98],"generation.":[100],"In":[101],"way,":[103],"process":[106],"maintains":[107],"high":[109],"temporal":[110],"resolution":[111],"features,":[114],"without":[115],"excessive":[116],"computational":[117],"requirements.":[118],"demonstrate":[120],"that":[121],"proposed":[123],"framework":[124],"achieves":[125],"state-of-the-art":[126],"results":[127],"benchmarks,":[130],"including":[131],"VoxCeleb2":[132],"and":[133],"LRS3,":[134],"producing":[135],"notably":[138],"better":[139],"naturalness.":[140],"Project":[141],"page":[142],"demo:":[144],"https://mm.kaist.ac.kr/projects/avdiffuss/":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
