{"id":"https://openalex.org/W4224920251","doi":"https://doi.org/10.1109/icassp43922.2022.9746866","title":"Time-Domain Audio-Visual Speech Separation on Low Quality Videos","display_name":"Time-Domain Audio-Visual Speech Separation on Low Quality Videos","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920251","doi":"https://doi.org/10.1109/icassp43922.2022.9746866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101452320","display_name":"Yifei Wu","orcid":"https://orcid.org/0009-0002-8201-6438"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050743863","display_name":"Jinfeng Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151703","display_name":"China Coal Technology and Engineering Group Corp (China)","ror":"https://ror.org/045d9gj14","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151703"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group,China","TAL Education Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group,China","institution_ids":["https://openalex.org/I4210151703"]},{"raw_affiliation_string":"TAL Education Group, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009659901","display_name":"Zhongqin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151703","display_name":"China Coal Technology and Engineering Group Corp (China)","ror":"https://ror.org/045d9gj14","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151703"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqin Wu","raw_affiliation_strings":["TAL Education Group,China","TAL Education Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group,China","institution_ids":["https://openalex.org/I4210151703"]},{"raw_affiliation_string":"TAL Education Group, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"256","last_page":"260"},"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":0.9983000159263611,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8607195019721985},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6922747492790222},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6079773306846619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5976640582084656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5783753991127014},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5355646014213562},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49159297347068787},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4737468659877777},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46864813566207886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46458035707473755},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4410141706466675},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3514188826084137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3449559211730957},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15349054336547852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607195019721985},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6922747492790222},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6079773306846619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5976640582084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5783753991127014},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5355646014213562},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49159297347068787},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4737468659877777},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46864813566207886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46458035707473755},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4410141706466675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3514188826084137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3449559211730957},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15349054336547852},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1991139021","https://openalex.org/W2221409856","https://openalex.org/W2408688265","https://openalex.org/W2460742184","https://openalex.org/W2551572271","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2964171275","https://openalex.org/W2972460025","https://openalex.org/W2972513594","https://openalex.org/W2973062255","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3015445830","https://openalex.org/W3015791137","https://openalex.org/W3057611960","https://openalex.org/W3097450720","https://openalex.org/W3099330747","https://openalex.org/W3151851237","https://openalex.org/W3160310387","https://openalex.org/W3160658686","https://openalex.org/W3163652268","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W3196777808","https://openalex.org/W4289665794","https://openalex.org/W4385245566","https://openalex.org/W6734790163","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2125195795"],"abstract_inverted_index":{"Incorporating":[0],"visual":[1,58,68,117],"information":[2],"is":[3,79,128],"a":[4,50],"promising":[5],"approach":[6],"to":[7,53,65,130],"improve":[8],"the":[9,37,55,62,72,82,109,114],"performance":[10,38],"of":[11,39,97],"speech":[12,42],"separation.":[13],"Many":[14],"related":[15],"works":[16],"have":[17],"been":[18],"conducted":[19],"and":[20,57,92,116,127],"provide":[21],"inspiring":[22],"results.":[23],"However,":[24],"low":[25,98,124,131],"quality":[26,99,125,132],"videos":[27],"appear":[28],"commonly":[29],"in":[30],"real":[31],"scenarios,":[32],"which":[33,60,111],"may":[34],"significantly":[35],"degrade":[36],"normal":[40,122],"audio-visual":[41],"separation":[43],"system.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"new":[51],"structure":[52],"fuse":[54],"audio":[56,63,115],"features,":[59],"uses":[61],"feature":[64],"select":[66],"relevant":[67],"features":[69,118],"by":[70],"utilizing":[71],"attention":[73],"mechanism.":[74],"A":[75],"Conv-TasNet":[76],"based":[77],"model":[78],"combined":[80],"with":[81,88,94,121],"proposed":[83],"attention-based":[84],"multi-modal":[85],"fusion,":[86],"trained":[87],"proper":[89],"data":[90],"augmentation":[91],"evaluated":[93],"3":[95],"categories":[96],"videos.":[100],"The":[101],"experimental":[102],"results":[103],"show":[104],"that":[105],"our":[106],"system":[107],"outperforms":[108],"baseline":[110],"simply":[112],"concatenates":[113],"when":[119],"training":[120],"or":[123],"data,":[126],"robust":[129],"video":[133],"inputs":[134],"at":[135],"inference":[136],"time.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
