{"id":"https://openalex.org/W3004910802","doi":"https://doi.org/10.1109/icassp40776.2020.9053396","title":"Source Separation with Weakly Labelled Data: an Approach to Computational Auditory Scene Analysis","display_name":"Source Separation with Weakly Labelled Data: an Approach to Computational Auditory Scene Analysis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3004910802","doi":"https://doi.org/10.1109/icassp40776.2020.9053396","mag":"3004910802"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053396","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/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375981","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-3060-4345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098658","display_name":"Xuchen Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuchen Song","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590005","display_name":"Yin Cao","orcid":"https://orcid.org/0000-0001-9086-7027"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yin Cao","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072482416"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7162,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95711679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6849398612976074},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6458224058151245},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.601195752620697},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5513743758201599},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5083336234092712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48481622338294983},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.4792371094226837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38963839411735535},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12608680129051208},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11395061016082764},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.10040915012359619},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08464515209197998},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07235905528068542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849398612976074},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6458224058151245},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.601195752620697},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5513743758201599},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5083336234092712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48481622338294983},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.4792371094226837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38963839411735535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12608680129051208},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11395061016082764},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.10040915012359619},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08464515209197998},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07235905528068542},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053396","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"},{"id":"pmh:oai:alma.44SUR_INST:11139680570002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:853783","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/853783/1/Source%20separation%20with%20weakly%20labelled%20data%20An%20approach%20to%20computational%20auditory%20scene%20analysis_v1.1.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3034362336","display_name":null,"funder_award_id":"EP/P022529/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1597158214","https://openalex.org/W1790748249","https://openalex.org/W1901129140","https://openalex.org/W2044893557","https://openalex.org/W2105892554","https://openalex.org/W2127851351","https://openalex.org/W2145905122","https://openalex.org/W2150415460","https://openalex.org/W2253434170","https://openalex.org/W2561557072","https://openalex.org/W2593116425","https://openalex.org/W2605138598","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2798158991","https://openalex.org/W2929983093","https://openalex.org/W2963723765","https://openalex.org/W2963750251","https://openalex.org/W2963933499","https://openalex.org/W2964121744","https://openalex.org/W2964159544","https://openalex.org/W2964229681","https://openalex.org/W2998657200","https://openalex.org/W3094550259","https://openalex.org/W3123940584","https://openalex.org/W3124794156","https://openalex.org/W4288375019","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6691781196","https://openalex.org/W6746448976","https://openalex.org/W6746914816","https://openalex.org/W6761152316","https://openalex.org/W6771438384","https://openalex.org/W7065181925"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1509813908","https://openalex.org/W1567098080","https://openalex.org/W1522062127","https://openalex.org/W2088740872","https://openalex.org/W2153297815","https://openalex.org/W614920976","https://openalex.org/W3004910802"],"abstract_inverted_index":{"Source":[0,14],"separation":[1,15,27,58,163],"is":[2,16,99,117,159],"the":[3,70,77,133,138,162],"task":[4],"of":[5,72,80,122,137,148,170],"separating":[6,31],"an":[7,73,167],"audio":[8,74,134],"recording":[9],"into":[10],"individual":[11],"sound":[12,33,81,87,95,112,149,175],"sources.":[13],"fundamental":[17],"for":[18,49,161],"computational":[19],"auditory":[20],"scene":[21],"analysis.":[22],"Previous":[23],"work":[24,42],"on":[25,30,132],"source":[26,47,57],"has":[28],"focused":[29],"particular":[32],"classes":[34,150,176],"such":[35],"as":[36],"speech":[37],"and":[38,45,165],"music.":[39],"Much":[40],"previous":[41],"requires":[43],"mixtures":[44],"clean":[46],"pairs":[48],"training.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"a":[56,86,110,115,120,128,154],"framework":[59],"trained":[60,94],"with":[61,91],"weakly":[62],"labelled":[63,66],"data.":[64],"Weakly":[65],"data":[67],"only":[68],"contains":[69],"tags":[71],"clip,":[75],"without":[76],"occurrence":[78],"time":[79],"events.":[82],"We":[83],"first":[84],"train":[85],"event":[88,96],"detection":[89,97],"system":[90,98,143,164],"AudioSet.":[92,178],"The":[93],"used":[100],"to":[101,108,127],"detect":[102],"segments":[103,126],"that":[104],"are":[105],"most":[106],"likely":[107],"contain":[109],"target":[111,129,139],"event.":[113],"Then":[114],"regression":[116],"learnt":[118],"from":[119,151],"mixture":[121],"two":[123],"randomly":[124],"selected":[125],"segment":[130],"conditioned":[131],"tagging":[135],"prediction":[136],"segment.":[140],"Our":[141],"proposed":[142],"can":[144],"separate":[145],"527":[146,174],"kinds":[147],"AudioSet":[152],"within":[153],"single":[155],"system.":[156],"A":[157],"U-Net":[158],"adopted":[160],"achieves":[166],"average":[168],"SDR":[169],"5.67":[171],"dB":[172],"over":[173],"in":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}