{"id":"https://openalex.org/W3015785290","doi":"https://doi.org/10.1109/icassp40776.2020.9053033","title":"A Robust Audio-Visual Speech Enhancement Model","display_name":"A Robust Audio-Visual Speech Enhancement Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015785290","doi":"https://doi.org/10.1109/icassp40776.2020.9053033","mag":"3015785290"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5006131727","display_name":"Wupeng Wang","orcid":"https://orcid.org/0009-0000-5360-2054"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wupeng Wang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107981608","display_name":"Chao Xing","orcid":"https://orcid.org/0000-0003-1120-8803"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Chao Xing","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391562","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0003-4872-4860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua Unviersity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua Unviersity","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768162","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0002-7634-9319"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113109420","display_name":"Fengyu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengyu Sun","raw_affiliation_strings":["Huawei Technologies CO. LTD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO. LTD","institution_ids":["https://openalex.org/I4210146936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7529","last_page":"7533"},"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":0.9979000091552734,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.855391263961792},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6748838424682617},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6437757611274719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6226146221160889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47959911823272705},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44030120968818665},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4304257929325104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3334769606590271},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14893555641174316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855391263961792},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6748838424682617},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6437757611274719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6226146221160889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47959911823272705},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44030120968818665},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4304257929325104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3334769606590271},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14893555641174316},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W1969975883","https://openalex.org/W2015394094","https://openalex.org/W2038010270","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2137400100","https://openalex.org/W2292405593","https://openalex.org/W2341528187","https://openalex.org/W2771039075","https://openalex.org/W2788241093","https://openalex.org/W2891433113","https://openalex.org/W2991015288","https://openalex.org/W3101998545","https://openalex.org/W3123318516","https://openalex.org/W4288103436","https://openalex.org/W4289665794","https://openalex.org/W6696765674","https://openalex.org/W6746717610","https://openalex.org/W6768074986"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W3011883280","https://openalex.org/W2369082698","https://openalex.org/W2401808953"],"abstract_inverted_index":{"Most":[0],"existing":[1],"audio-visual":[2],"speech":[3,77,104,190],"enhancement":[4],"(AVSE)":[5],"methods":[6],"work":[7],"well":[8],"in":[9,80,174,189],"conditions":[10,18,81],"with":[11,19],"strong":[12,50],"noise,":[13],"however":[14],"when":[15],"applied":[16],"to":[17,35,75,138,185],"a":[20,64,100,129,143,182],"medium":[21],"SNR,":[22],"serious":[23],"performance":[24,151],"degradations":[25,30],"are":[26],"often":[27],"observed.":[28],"These":[29],"can":[31,69,118],"be":[32,119],"partly":[33],"attributed":[34],"the":[36,44,52,71,110,113,123,135,139,149,155,161,171],"feature-fusion(early":[37],"fusion":[38],"etc.)":[39],"architecture":[40,132],"that":[41,47,55,68,133,165,179],"tightly":[42],"couples":[43],"audio":[45,76],"information":[46,54,115],"is":[48,56,90,152,181],"very":[49],"and":[51,116],"visual":[53,72,114,124,187],"relatively":[57],"weak.":[58],"In":[59],"this":[60,147,166],"paper,":[61],"we":[62,93,127],"present":[63],"safe":[65,183],"AVSE":[66],"approach":[67,168],"make":[70],"stream":[73],"contribute":[74],"enhancment(ASE)":[78],"safely":[79],"of":[82,103,112],"various":[83],"SNRs":[84],"by":[85,154],"late":[86],"fusion.The":[87],"key":[88],"novelty":[89],"two-fold:":[91],"Firstly,":[92],"define":[94],"power":[95],"binary":[96],"masks":[97,141],"(PBMs)":[98],"as":[99],"rough":[101,107],"representation":[102,108],"signals.":[105],"This":[106],"admits":[109],"weakness":[111],"so":[117],"easily":[120],"predicted":[121],"from":[122],"stream.":[125],"Secondly,":[126],"design":[128],"posterior":[130],"augmentation":[131],"integrate":[134],"visual-derived":[136],"PBMs":[137],"audio-derived":[140],"via":[142],"gating":[144],"network.":[145],"By":[146],"architecture,":[148],"entire":[150],"lower-bounded":[153],"audio-based":[156,172],"component.":[157],"Our":[158],"experiments":[159],"on":[160],"Grid":[162],"dataset":[163],"demonstrated":[164],"new":[167],"consistently":[169],"outperforms":[170],"system":[173],"all":[175],"noise":[176],"conditions,":[177],"confirming":[178],"it":[180],"way":[184],"incorporate":[186],"knowledge":[188],"enhancement.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}