{"id":"https://openalex.org/W3201437620","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533660","title":"Audio-Visual Speech Separation with Visual Features Enhanced by Adversarial Training","display_name":"Audio-Visual Speech Separation with Visual Features Enhanced by Adversarial Training","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201437620","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533660","mag":"3201437620"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5100364263","display_name":"Peng Zhang","orcid":"https://orcid.org/0009-0000-3326-4983"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101746187","display_name":"Jiaming Xu","orcid":"https://orcid.org/0000-0001-7635-1059"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112122495","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0003-3225-7145"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059162334","display_name":"Yunzhe Hao","orcid":"https://orcid.org/0000-0001-7824-6965"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhe Hao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067662662","display_name":"Lei Qin","orcid":"https://orcid.org/0000-0002-3902-3192"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Qin","raw_affiliation_strings":["Huawei Consumer Business Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Consumer Business Group, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635207","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6379-7617"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, CAS, China","Institute of Automation, Chinese Academy of Science, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, CAS, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62534511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9980999827384949,"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":0.9980000257492065,"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":0.8610125780105591},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7004309296607971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6215256452560425},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5765466094017029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429331064224243},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5089011192321777},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49790000915527344},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49037623405456543},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.21368932723999023},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13388678431510925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610125780105591},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7004309296607971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6215256452560425},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5765466094017029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429331064224243},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5089011192321777},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49037623405456543},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.21368932723999023},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13388678431510925},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1558945660","https://openalex.org/W1971168548","https://openalex.org/W1991139021","https://openalex.org/W2002621203","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2029199293","https://openalex.org/W2038010270","https://openalex.org/W2099128937","https://openalex.org/W2115252128","https://openalex.org/W2118877769","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2154151281","https://openalex.org/W2166579744","https://openalex.org/W2341528187","https://openalex.org/W2460742184","https://openalex.org/W2515770085","https://openalex.org/W2585824449","https://openalex.org/W2593116425","https://openalex.org/W2593414223","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2620711924","https://openalex.org/W2734774145","https://openalex.org/W2844030168","https://openalex.org/W2890952074","https://openalex.org/W2894798093","https://openalex.org/W2900292050","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963082324","https://openalex.org/W2963290645","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2972513594","https://openalex.org/W2973231102","https://openalex.org/W2998161426","https://openalex.org/W3008400075","https://openalex.org/W3024147341","https://openalex.org/W3035268204","https://openalex.org/W3040777582","https://openalex.org/W3096214032","https://openalex.org/W3097797867","https://openalex.org/W3099330747","https://openalex.org/W3101998545","https://openalex.org/W3163287738","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6675117242","https://openalex.org/W6677548441","https://openalex.org/W6677618333","https://openalex.org/W6734564793","https://openalex.org/W6739235094","https://openalex.org/W6754392867","https://openalex.org/W6774995033","https://openalex.org/W6777308879","https://openalex.org/W6780413204","https://openalex.org/W6784297428"],"related_works":["https://openalex.org/W2955938200","https://openalex.org/W2748454020","https://openalex.org/W2963891724","https://openalex.org/W2170796342","https://openalex.org/W3019117105","https://openalex.org/W2521154689","https://openalex.org/W4304891817","https://openalex.org/W4294892203","https://openalex.org/W2747876639","https://openalex.org/W2125537957"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,115,154],"separation":[2,116,155],"(AVSS)":[3],"refers":[4],"to":[5,37,43,99,164],"separating":[6],"individual":[7],"voice":[8],"from":[9],"an":[10,29],"audio":[11],"mixture":[12],"of":[13,69,169,176],"multiple":[14],"simultaneous":[15],"talkers":[16],"by":[17,87,173],"conditioning":[18],"on":[19,33,125],"visual":[20,26,41,59,72,81,104],"features.":[21],"For":[22],"the":[23,45,63,67,80,95,109,166,174],"AVSS":[24,54,143,170],"task,":[25],"features":[27,42,60,73,82,105],"play":[28],"important":[30],"role,":[31],"based":[32],"which":[34,185],"we":[35,50,78,93,180],"manage":[36],"extract":[38,79],"more":[39],"effective":[40],"improve":[44],"performance.":[46],"In":[47],"this":[48],"paper,":[49],"propose":[51,181],"a":[52,182],"novel":[53],"model":[55,138,150,188],"that":[56,83,136,148],"uses":[57],"speech-related":[58,71,85,101],"for":[61],"isolating":[62],"target":[64],"speaker.":[65],"Specifically,":[66],"method":[68,98],"extracting":[70],"has":[74],"two":[75],"steps.":[76],"Firstly,":[77],"contain":[84],"information":[86,102],"learning":[88],"joint":[89],"audio-visual":[90,114,127],"representation.":[91],"Secondly,":[92],"use":[94],"adversarial":[96],"training":[97,183],"enhance":[100],"in":[103,157,162],"further.":[106],"We":[107,145],"adopt":[108],"time-domain":[110],"approach":[111],"and":[112,133,199],"build":[113],"networks":[117,122],"with":[118],"temporal":[119],"convolutional":[120],"neural":[121],"block.":[123],"Experiments":[124],"four":[126],"datasets,":[128],"including":[129],"GRID,":[130],"TCD-TIMIT,":[131],"AVSpeech,":[132],"LRS2,":[134],"show":[135],"our":[137,149,187],"significantly":[139],"outperforms":[140],"previous":[141],"state-of-the-art":[142],"models.":[144],"also":[146],"demonstrate":[147],"can":[151,202],"achieve":[152],"excellent":[153],"performance":[156,167],"noisy":[158],"realworld":[159],"scenarios.":[160],"Moreover,":[161],"order":[163],"alleviate":[165],"degradation":[168],"models":[171],"caused":[172],"missing":[175],"some":[177],"video":[178,191],"frames,":[179],"strategy,":[184],"makes":[186],"robust":[189],"when":[190],"frames":[192],"are":[193],"partially":[194],"missing.":[195],"The":[196],"demo,":[197],"code,":[198],"supplementary":[200],"materials":[201],"be":[203],"available":[204],"at":[205],"https://github.com/aispeech-lab/advr-avss.":[206]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}