{"id":"https://openalex.org/W3210206437","doi":"https://doi.org/10.1109/mapr53640.2021.9585244","title":"Visual-guided audio source separation: an empirical study","display_name":"Visual-guided audio source separation: an empirical study","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3210206437","doi":"https://doi.org/10.1109/mapr53640.2021.9585244","mag":"3210206437"},"language":"en","primary_location":{"id":"doi:10.1109/mapr53640.2021.9585244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr53640.2021.9585244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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/A5003217635","display_name":"Thanh Thi Duong","orcid":"https://orcid.org/0000-0001-5854-5845"},"institutions":[{"id":"https://openalex.org/I29199639","display_name":"Hanoi University of Mining and Geology","ror":"https://ror.org/01rw3qm79","country_code":"VN","type":"education","lineage":["https://openalex.org/I29199639"]},{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Thanh Thi-Hien Duong","raw_affiliation_strings":["Hanoi University of Mining and Geology,Dept. Information Technology,Hanoi,Vietnam","MICA, Hanoi University of Science and Technology, Hanoi, Vietnam","Dept. Information Technology, Hanoi University of Mining and Geology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Mining and Geology,Dept. Information Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I29199639"]},{"raw_affiliation_string":"MICA, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Dept. Information Technology, Hanoi University of Mining and Geology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I29199639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108766706","display_name":"Manh Nguyen Huu","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Manh Nguyen Huu","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information Technology,Hanoi,Vietnam","School of Information Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087402762","display_name":"Hai Nghiem Thi","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hai Nghiem Thi","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Electrical Engineering,Hanoi,Vietnam","School of Electrical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Electrical Engineering,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Electrical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067859504","display_name":"Thi\u2010Lan Le","orcid":"https://orcid.org/0000-0001-9541-3905"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thi-Lan Le","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Electronics and Telecommunications,Hanoi,Vietnam","School of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, Vietnam","MICA, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Electronics and Telecommunications,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"MICA, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058485829","display_name":"Phi Le Nguyen","orcid":"https://orcid.org/0000-0001-6547-7641"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phi-Le Nguyen","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Information Technology,Hanoi,Vietnam","School of Information Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Information Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Information Technology, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101764507","display_name":"Quoc Cuong Nguyen","orcid":"https://orcid.org/0000-0002-5641-5040"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc-Cuong Nguyen","raw_affiliation_strings":["Hanoi University of Science and Technology,School of Electrical Engineering,Hanoi,Vietnam","School of Electrical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,School of Electrical Engineering,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"School of Electrical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003217635"],"corresponding_institution_ids":["https://openalex.org/I29199639","https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62386748,"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":"1","last_page":"6"},"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":0.9991999864578247,"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":0.9966999888420105,"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":0.8293519616127014},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6891544461250305},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6747986674308777},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6657374501228333},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5818215608596802},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5502625703811646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120819211006165},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5034422278404236},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4948381781578064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48003852367401123},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4389399588108063},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4307253062725067},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4040864408016205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20720595121383667},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1763811707496643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06671866774559021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293519616127014},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6891544461250305},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6747986674308777},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6657374501228333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5818215608596802},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5502625703811646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120819211006165},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5034422278404236},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4948381781578064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48003852367401123},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4389399588108063},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4307253062725067},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4040864408016205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20720595121383667},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1763811707496643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06671866774559021},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr53640.2021.9585244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr53640.2021.9585244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309617","display_name":"National Foundation for Science and Technology Development","ror":"https://ror.org/04rw64z44"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2168818958","https://openalex.org/W2194775991","https://openalex.org/W2285479626","https://openalex.org/W2591920181","https://openalex.org/W2644497536","https://openalex.org/W2660943524","https://openalex.org/W2796347433","https://openalex.org/W2891508564","https://openalex.org/W2904140938","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2963218389","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2988200020","https://openalex.org/W3017343282","https://openalex.org/W3018757597","https://openalex.org/W3024147341","https://openalex.org/W3099330747","https://openalex.org/W3113792747","https://openalex.org/W3116298410","https://openalex.org/W3123318516","https://openalex.org/W3182657421","https://openalex.org/W4285827580","https://openalex.org/W4289665794","https://openalex.org/W4293584584","https://openalex.org/W4293665662","https://openalex.org/W6684447540","https://openalex.org/W6729831399","https://openalex.org/W6750227808","https://openalex.org/W6777046832","https://openalex.org/W6779206265","https://openalex.org/W6782004394","https://openalex.org/W6788484017"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Real-world":[0],"video":[1],"scenes":[2],"are":[3,9,30,90],"usually":[4],"very":[5,61],"complicated":[6],"as":[7,42,112],"they":[8],"mixtures":[10],"of":[11,45,70,80,103,120,138],"many":[12],"different":[13,81,104],"audio-visual":[14],"objects.":[15],"Humans":[16],"with":[17],"normal":[18],"hearing":[19],"ability":[20],"can":[21,50],"easily":[22],"locate,":[23],"identify":[24],"and":[25],"differentiate":[26],"sound":[27,53,95],"sources":[28,54],"which":[29],"heard":[31],"simultaneously.":[32],"However,":[33],"this":[34,64],"is":[35],"an":[36,113],"extremely":[37],"difficult":[38,56],"task":[39],"for":[40,77,107],"machines":[41],"the":[43,68,84,94,101,108,118,136,139,145],"creation":[44],"machine":[46],"listening":[47],"algorithms":[48],"that":[49],"automatically":[51],"separate":[52],"in":[55,83,144],"mixing":[57],"conditions":[58],"has":[59],"remained":[60],"challenging.":[62],"In":[63,110],"paper,":[65],"we":[66,116],"consider":[67],"use":[69,102],"a":[71,131],"visual-guided":[72],"audio":[73],"source":[74],"separation":[75,96,124],"approach":[76],"separating":[78],"sounds":[79],"instruments":[82],"video,":[85],"where":[86],"detected":[87],"visual":[88],"objects":[89],"used":[91],"to":[92],"assist":[93],"process.":[97],"We":[98],"particularly":[99],"investigate":[100],"object":[105,141],"detectors":[106],"task.":[109],"addition,":[111],"empirical":[114],"study,":[115],"analyze":[117],"effect":[119],"training":[121],"datasets":[122],"on":[123],"performance.":[125],"Finally,":[126],"experiment":[127],"results":[128],"obtained":[129],"from":[130],"benchmark":[132],"dataset":[133],"MUSIC":[134],"confirm":[135],"advantages":[137],"new":[140],"detector":[142],"investigated":[143],"paper.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
