{"id":"https://openalex.org/W4404317174","doi":"https://doi.org/10.1109/taslp.2024.3497586","title":"CLAPSep: Leveraging Contrastive Pre-Trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","display_name":"CLAPSep: Leveraging Contrastive Pre-Trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404317174","doi":"https://doi.org/10.1109/taslp.2024.3497586"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3497586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3497586","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101108881","display_name":"Hao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ma","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0001-2651-8524","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075223216","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-9870-4422"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699660","display_name":"Li Xu","orcid":"https://orcid.org/0000-0003-2954-3271"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["ARC Laboratory, Tencent PCG, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2954-3271","affiliations":[{"raw_affiliation_string":"ARC Laboratory, Tencent PCG, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025217534","display_name":"Mingjie Shao","orcid":"https://orcid.org/0000-0003-0659-5765"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Shao","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0659-5765","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"raw_affiliation_string":"Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763011","display_name":"Ju Liu","orcid":"https://orcid.org/0000-0003-3160-9233"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Liu","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3160-9233","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3493,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96705791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"4945","last_page":"4960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9718000292778015,"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/modal","display_name":"Modal","score":0.6706752181053162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6706255078315735},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6369328498840332},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4475197196006775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837069272994995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.364810049533844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34657734632492065},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21735471487045288},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07910680770874023},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06801155209541321},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.04956987500190735}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6706752181053162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706255078315735},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6369328498840332},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4475197196006775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837069272994995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.364810049533844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34657734632492065},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21735471487045288},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07910680770874023},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06801155209541321},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.04956987500190735},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3497586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3497586","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3265829877","display_name":null,"funder_award_id":"ZR2023QF103","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2033875152","https://openalex.org/W2052666245","https://openalex.org/W2187089797","https://openalex.org/W2460742184","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2796571515","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2998657200","https://openalex.org/W3095263845","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3138516171","https://openalex.org/W3163652268","https://openalex.org/W4224871700","https://openalex.org/W4226058394","https://openalex.org/W4226151502","https://openalex.org/W4226442948","https://openalex.org/W4289242435","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4312420092","https://openalex.org/W4312960937","https://openalex.org/W4372260051","https://openalex.org/W4372260310","https://openalex.org/W4372348953","https://openalex.org/W4375928773","https://openalex.org/W4376632781","https://openalex.org/W4385245566","https://openalex.org/W4387634373","https://openalex.org/W4391631676","https://openalex.org/W4392902953","https://openalex.org/W4392903216","https://openalex.org/W4392904451","https://openalex.org/W4392909554","https://openalex.org/W4392909615","https://openalex.org/W4392910302","https://openalex.org/W4396877837","https://openalex.org/W6753583920","https://openalex.org/W6756251360","https://openalex.org/W6757817989","https://openalex.org/W6784499681","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6801426729","https://openalex.org/W6840561836","https://openalex.org/W6847370424","https://openalex.org/W6849109464","https://openalex.org/W6852871851","https://openalex.org/W6857534457","https://openalex.org/W6860678771","https://openalex.org/W6861273229","https://openalex.org/W6869897819"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Universal":[0],"sound":[1,21,48,74,135],"separation":[2,42,78],"(USS)":[3],"aims":[4],"to":[5,67,85,92,165],"extract":[6],"arbitrary":[7],"types":[8],"of":[9,27,129,140,154,175],"sounds":[10],"from":[11,55],"real-world":[12],"recordings.":[13],"This":[14],"can":[15,142],"be":[16,98],"achieved":[17],"by":[18,186],"language-queried":[19],"target":[20,47,134],"extraction":[22,147],"(TSE),":[23],"which":[24],"typically":[25],"consists":[26],"two":[28],"components:":[29],"a":[30,41,58,187],"query":[31],"network":[32,43],"that":[33,44],"converts":[34],"user":[35,120,127],"queries":[36],"into":[37,89],"conditional":[38],"embeddings,":[39],"and":[40,62,76,102,125,170,172,192,200],"extracts":[45],"the":[46,69,94,104,146,152,167],"accordingly.":[49,79],"Existing":[50],"methods":[51,185],"commonly":[52],"train":[53],"models":[54,88,91],"scratch.":[56],"As":[57],"consequence,":[59],"substantial":[60],"data":[61],"computational":[63],"resources":[64],"are":[65,196],"required":[66],"make":[68],"randomly":[70],"initialized":[71],"model":[72,109],"comprehend":[73],"events":[75],"perform":[77],"In":[80],"this":[81],"paper,":[82],"we":[83,100],"propose":[84],"integrate":[86],"pre-trained":[87,108],"TSE":[90],"address":[93],"above":[95],"issue.":[96],"To":[97],"specific,":[99],"tailor":[101],"adapt":[103],"powerful":[105],"contrastive":[106],"language-audio":[107],"(CLAP)":[110],"for":[111,133,198],"USS,":[112],"denoted":[113],"as":[114],"CLAPSep.":[115],"CLAPSep":[116,141,178],"also":[117,150],"accepts":[118],"flexible":[119],"inputs,":[121],"taking":[122],"both":[123],"positive":[124],"negative":[126],"prompts":[128],"uni-":[130],"and/or":[131],"multi-modalities":[132],"extraction.":[136],"These":[137],"key":[138],"features":[139],"not":[143],"only":[144],"enhance":[145],"performance":[148,169],"but":[149],"improve":[151],"versatility":[153],"its":[155],"application.":[156],"We":[157],"provide":[158],"extensive":[159],"experiments":[160],"on":[161],"5":[162],"diverse":[163],"datasets":[164],"demonstrate":[166],"superior":[168],"zero-":[171],"few-shot":[173],"generalizability":[174],"our":[176],"proposed":[177],"with":[179],"fast":[180],"training":[181],"convergence,":[182],"surpassing":[183],"previous":[184],"significant":[188],"margin.":[189],"Full":[190],"codes":[191],"some":[193],"audio":[194],"examples":[195],"released":[197],"reproduction":[199],"evaluation.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}