{"id":"https://openalex.org/W3015529133","doi":"https://doi.org/10.1109/icassp40776.2020.9054263","title":"A Visual-Pilot Deep Fusion for Target Speech Separation in Multitalker Noisy Environment","display_name":"A Visual-Pilot Deep Fusion for Target Speech Separation in Multitalker Noisy Environment","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015529133","doi":"https://doi.org/10.1109/icassp40776.2020.9054263","mag":"3015529133"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054263","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/A5100369235","display_name":"Yun Li","orcid":"https://orcid.org/0000-0003-1490-2657"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun Li","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119269608","display_name":"Zhang Liu","orcid":"https://orcid.org/0009-0008-6302-5818"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang Liu","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025634497","display_name":"Yueyue Na","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueyue Na","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673728","display_name":"Ziteng Wang","orcid":"https://orcid.org/0009-0001-8487-8093"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziteng Wang","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069657933","display_name":"Biao Tian","orcid":"https://orcid.org/0000-0001-7259-3739"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biao Tian","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101844257","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0001-7780-7185"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100369235"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.59289006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4442","last_page":"4446"},"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":0.9977999925613403,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9958999752998352,"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":0.7777516841888428},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6216155886650085},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5729696750640869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5380008220672607},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5143347978591919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49799299240112305},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4956146478652954},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.47055935859680176},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4668387174606323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29958266019821167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777516841888428},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6216155886650085},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5729696750640869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5380008220672607},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5143347978591919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799299240112305},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4956146478652954},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.47055935859680176},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4668387174606323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29958266019821167},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054263","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":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W133022121","https://openalex.org/W185399533","https://openalex.org/W653761051","https://openalex.org/W1552314771","https://openalex.org/W1971168548","https://openalex.org/W2015143272","https://openalex.org/W2031647436","https://openalex.org/W2099940393","https://openalex.org/W2127851351","https://openalex.org/W2146203184","https://openalex.org/W2164598857","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2585824449","https://openalex.org/W2604169470","https://openalex.org/W2619697695","https://openalex.org/W2734774145","https://openalex.org/W2747876639","https://openalex.org/W2788241093","https://openalex.org/W2844030168","https://openalex.org/W2889206679","https://openalex.org/W2901702433","https://openalex.org/W2962866211","https://openalex.org/W2963019222","https://openalex.org/W2963082324","https://openalex.org/W2964207404","https://openalex.org/W2973084105","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6607486085","https://openalex.org/W6688816777","https://openalex.org/W6688843265","https://openalex.org/W6718827390","https://openalex.org/W6743462201"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Separating":[0],"the":[1,23,27,33,39,52,58,65,87,102,107,114,118,125,134],"target":[2,69,119],"speech":[3,25,120],"in":[4,71,97,141],"multi-talker":[5,72],"noisy":[6,73],"environment":[7],"is":[8,21,76,81,122,131],"a":[9],"challenging":[10,98],"problem":[11,19],"for":[12],"audio-only":[13],"source":[14],"separation":[15,95],"algorithms.":[16],"The":[17],"major":[18],"behind":[20],"that":[22,78,113],"separated":[24],"from":[26],"same":[28],"talker":[29,40,88],"can":[30],"switch":[31],"among":[32],"outputs":[34],"across":[35],"consecutive":[36],"segments,":[37],"causing":[38],"permutation":[41,89],"issue.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"deploy":[47],"face":[48],"tracking":[49],"and":[50,57],"propose":[51],"low-dimension":[53],"hand-crafted":[54],"visual":[55],"features":[56],"low-cost":[59],"deep":[60],"fusion":[61],"architectures":[62],"to":[63],"separate":[64],"unseen":[66],"but":[67,91],"visible":[68,137],"sources":[70,138],"environment.":[74],"It":[75],"shown":[77],"our":[79],"approach":[80],"not":[82],"only":[83],"capable":[84],"of":[85,117,133,136],"addressing":[86],"issue":[90],"also":[92,111],"producing":[93],"additional":[94],"improvement":[96,116],"mixtures":[99],"such":[100],"as":[101],"same-gender":[103],"overlapping":[104],"ones":[105],"on":[106,124],"public":[108],"dataset.":[109,128],"We":[110],"show":[112],"significant":[115],"recognition":[121],"achieved":[123],"simulated":[126],"real-world":[127],"Our":[129],"training":[130],"independent":[132],"number":[135],"providing":[139],"flexibility":[140],"deployment.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
