{"id":"https://openalex.org/W3024147341","doi":"https://doi.org/10.21437/interspeech.2020-1065","title":"FaceFilter: Audio-Visual Speech Separation Using Still Images","display_name":"FaceFilter: Audio-Visual Speech Separation Using Still Images","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3024147341","doi":"https://doi.org/10.21437/interspeech.2020-1065","mag":"3024147341"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1065","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.07074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046276512","display_name":"Soo-Whan Chung","orcid":"https://orcid.org/0000-0001-6529-2196"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soo-Whan Chung","raw_affiliation_strings":["Department of Electrical & Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022555543","display_name":"Soyeon Choe","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Choe","raw_affiliation_strings":["Naver Corp., Seongnam-si, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corp., Seongnam-si, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"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/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corp., Seongnam-si, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corp., Seongnam-si, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical & Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046276512"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":7.0095,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.97873454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3481","last_page":"3485"},"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":0.9987000226974487,"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":0.9957000017166138,"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":0.7888005971908569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7201955318450928},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5755689144134521},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5301650166511536},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.47748348116874695},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4702642858028412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46630966663360596},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.466054767370224},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42869511246681213},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4123893976211548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888005971908569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7201955318450928},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5755689144134521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5301650166511536},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.47748348116874695},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4702642858028412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46630966663360596},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.466054767370224},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42869511246681213},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4123893976211548},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1065","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.07074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07074","pdf_url":"https://arxiv.org/pdf/2005.07074","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.07074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07074","pdf_url":"https://arxiv.org/pdf/2005.07074","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2082183045","https://openalex.org/W2120847449","https://openalex.org/W2150769028","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2597655663","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2793493229","https://openalex.org/W2796992393","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2956679704","https://openalex.org/W2959214850","https://openalex.org/W2962824709","https://openalex.org/W2962918445","https://openalex.org/W2962935966","https://openalex.org/W2962960500","https://openalex.org/W2963082324","https://openalex.org/W2963173190","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W2973062255","https://openalex.org/W2979157532","https://openalex.org/W3015734344","https://openalex.org/W3015915076","https://openalex.org/W3016663370","https://openalex.org/W3099206234","https://openalex.org/W3105928222","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"The":[0,115],"objective":[1],"of":[2,15,50],"this":[3,55],"paper":[4],"is":[5,60,118,142],"to":[6,88],"separate":[7],"a":[8,13,19,46],"target":[9,52],"speaker's":[10],"speech":[11,22,112,124],"from":[12,62,82,96],"mixture":[14],"two":[16],"speakers":[17,91,148],"using":[18],"deep":[20],"audio-visual":[21],"separation":[23,113,125,139,145],"network.":[24],"Unlike":[25],"previous":[26],"works":[27],"that":[28],"used":[29],"lip":[30],"movement":[31],"on":[32,133,144,162],"video":[33],"clips":[34],"or":[35],"pre-enrolled":[36],"speaker":[37],"information":[38],"as":[39],"an":[40],"auxiliary":[41],"conditional":[42,58],"feature,":[43],"we":[44],"use":[45],"single":[47],"face":[48],"image":[49],"the":[51,57,86,94,101],"speaker.":[53],"In":[54],"task,":[56,68],"feature":[59],"obtained":[61],"facial":[63,83],"appearance":[64],"in":[65,77,111],"cross-modal":[66],"biometric":[67],"where":[69],"audio":[70],"and":[71,92,159],"visual":[72],"identity":[73],"representations":[74],"are":[75,130],"shared":[76],"latent":[78],"space.":[79],"Learnt":[80],"identities":[81],"images":[84,129],"enforce":[85],"network":[87],"isolate":[89],"matched":[90],"extract":[93],"voices":[95],"mixed":[97],"speech.":[98],"It":[99],"solves":[100],"permutation":[102],"problem":[103],"caused":[104],"by":[105],"swapped":[106],"channel":[107],"outputs,":[108],"frequently":[109],"occurred":[110],"tasks.":[114],"proposed":[116],"method":[117],"far":[119],"more":[120],"practical":[121],"than":[122],"video-based":[123],"since":[126],"user":[127],"profile":[128],"readily":[131],"available":[132],"many":[134],"platforms.":[135],"Also,":[136],"unlike":[137],"speaker-aware":[138],"methods,":[140],"it":[141],"applicable":[143],"with":[146],"unseen":[147],"who":[149],"have":[150],"never":[151],"been":[152],"enrolled":[153],"before.":[154],"We":[155],"show":[156],"strong":[157],"qualitative":[158],"quantitative":[160],"results":[161],"challenging":[163],"real-world":[164],"examples.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
