{"id":"https://openalex.org/W3015445830","doi":"https://doi.org/10.1109/icassp40776.2020.9054180","title":"Deep Audio-Visual Speech Separation with Attention Mechanism","display_name":"Deep Audio-Visual Speech Separation with Attention Mechanism","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015445830","doi":"https://doi.org/10.1109/icassp40776.2020.9054180","mag":"3015445830"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054180","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":"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/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":true,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence SpeechLab,Shanghai,China","MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence SpeechLab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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 SpeechLab,Shanghai,China","MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence SpeechLab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090224430"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.7884,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94081633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7314","last_page":"7318"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394771218299866},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.8136530518531799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.697813868522644},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5781395435333252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5199840664863586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45071232318878174},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4417247474193573},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.42654505372047424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19084224104881287},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12106978893280029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394771218299866},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8136530518531799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.697813868522644},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5781395435333252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5199840664863586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45071232318878174},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4417247474193573},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.42654505372047424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19084224104881287},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12106978893280029},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054180","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":[{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1552314771","https://openalex.org/W1971168548","https://openalex.org/W1991139021","https://openalex.org/W2133564696","https://openalex.org/W2147527908","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2211192759","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2734774145","https://openalex.org/W2804228164","https://openalex.org/W2808631503","https://openalex.org/W2889503488","https://openalex.org/W2892163332","https://openalex.org/W2892356933","https://openalex.org/W2951527505","https://openalex.org/W2952746495","https://openalex.org/W2962715207","https://openalex.org/W2962826786","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963843276","https://openalex.org/W2964171275","https://openalex.org/W2964308564","https://openalex.org/W4289665794","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6682137061","https://openalex.org/W6686509673","https://openalex.org/W6734491695"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Previous":[0],"work":[1],"shows":[2],"that":[3,93],"audio-visual":[4,86,100],"fusion":[5],"is":[6,82],"a":[7,27],"practical":[8],"approach":[9,96],"to":[10,30,39,117],"deal":[11],"with":[12,34],"the":[13,18,35,40,49,57,63,77,79,85,94,118,123],"speech":[14,71,87,101,113],"separation":[15,88,114],"task":[16],"in":[17,56,99,112],"cocktail":[19],"party":[20],"problem.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"explore":[26],"better":[28],"strategy":[29],"utilize":[31],"visual":[32,46,54,126],"representations":[33],"attention":[36,80],"mechanism.":[37],"Compared":[38],"previous":[41],"baseline":[42],"only":[43,121],"using":[44,122],"one":[45],"stream":[47],"of":[48],"target":[50,124],"speaker,":[51],"both":[52],"speaker-dependent":[53],"streams":[55,72],"mixed":[58],"audio":[59],"are":[60],"fed":[61],"into":[62],"model,":[64],"and":[65,109],"it":[66],"also":[67],"predicts":[68],"two":[69],"separated":[70],"simultaneously.":[73],"To":[74],"further":[75],"enhance":[76],"performance,":[78],"mechanism":[81],"designed":[83],"on":[84],"architecture.":[89],"The":[90],"results":[91],"show":[92],"proposed":[95],"works":[97],"well":[98],"separation.":[102],"Our":[103],"best":[104],"model":[105],"achieves":[106],"an":[107],"obvious":[108],"consistent":[110],"improvement":[111],"when":[115],"compared":[116],"traditional":[119],"method":[120],"speaker":[125],"stream.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
