{"id":"https://openalex.org/W4408353777","doi":"https://doi.org/10.1109/icassp49660.2025.10887543","title":"Language-Queried Target Sound Extraction Without Parallel Training Data","display_name":"Language-Queried Target Sound Extraction Without Parallel Training Data","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353777","doi":"https://doi.org/10.1109/icassp49660.2025.10887543"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":["Shandong University,School of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106713617","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-5133-9237"},"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":["North Carolina State University,Department of Computer Science,North Carolina,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,North Carolina,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":["Tencent PCG,ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003437466","display_name":"Yukai Li","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":"Yukai Li","raw_affiliation_strings":["Shandong University,School of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Shao","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of System and Control, AMSS,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of System and Control, AMSS,Beijing,China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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":"Qiuqiang Kong","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","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":["Shandong University,School of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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":0.995199978351593,"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":0.978600025177002,"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":0.8279273509979248},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5421268939971924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5064574480056763},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.447163462638855},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4443184733390808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3749748468399048},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3663700819015503},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07307958602905273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279273509979248},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5421268939971924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5064574480056763},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.447163462638855},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4443184733390808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3749748468399048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3663700819015503},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07307958602905273},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2796571515","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2998657200","https://openalex.org/W3015591594","https://openalex.org/W3095263845","https://openalex.org/W3163652268","https://openalex.org/W4224871700","https://openalex.org/W4226151502","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4312438583","https://openalex.org/W4372259805","https://openalex.org/W4372260310","https://openalex.org/W4372348953","https://openalex.org/W4375928773","https://openalex.org/W4385567053","https://openalex.org/W4392909554","https://openalex.org/W4400033239","https://openalex.org/W4404317174","https://openalex.org/W4405934446","https://openalex.org/W6801426729","https://openalex.org/W6810452849","https://openalex.org/W6847370424","https://openalex.org/W6849109464","https://openalex.org/W6852871851","https://openalex.org/W6860678771"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W3216976533","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Language-queried":[0],"target":[1,58,132,163],"sound":[2],"extraction":[3],"(TSE)":[4],"aims":[5],"to":[6,68,124,172],"extract":[7],"specific":[8],"sounds":[9],"from":[10,107,169],"mixtures":[11],"based":[12],"on":[13],"language":[14,77,158],"queries.":[15],"Traditional":[16],"fully-supervised":[17],"training":[18,33,43,56,181],"schemes":[19],"require":[20],"extensively":[21],"annotated":[22],"parallel":[23],"audio-text":[24],"data,":[25],"which":[26,100],"are":[27,79],"labor-intensive.":[28],"We":[29],"introduce":[30],"a":[31,53,70,142,156],"parallel-data-free":[32,55],"scheme,":[34],"requiring":[35],"only":[36],"unlabelled":[37],"audio":[38,59,66,98,117,133,152,164],"clips":[39],"for":[40],"TSE":[41],"model":[42,50,159],"by":[44,81,155],"utilizing":[45],"the":[46,63,86,110,119,125],"contrastive":[47],"language-audio":[48],"pre-trained":[49,64],"(CLAP).":[51],"In":[52],"vanilla":[54,90],"stage,":[57],"is":[60,101],"encoded":[61,80],"using":[62,151],"CLAP":[65,82],"encoder":[67,84],"form":[69],"condition":[71,87,175],"embedding,":[72],"while":[73],"during":[74,135],"testing,":[75],"user":[76],"queries":[78],"text":[83,96,115,167],"as":[85,174],"embedding.":[88],"This":[89],"approach":[91,195],"assumes":[92],"perfect":[93],"alignment":[94],"between":[95,114,180],"and":[97,116,118,182,184,198],"embeddings,":[99,176],"unrealistic.":[102],"Two":[103],"major":[104],"challenges":[105],"arise":[106],"training-testing":[108],"mismatch:":[109],"persistent":[111],"modality":[112],"gap":[113],"risk":[120],"of":[121,127],"overfitting":[122],"due":[123],"exposure":[126],"rich":[128],"acoustic":[129],"details":[130],"in":[131],"embedding":[134,149],"training.":[136],"To":[137],"address":[138],"this,":[139],"we":[140,146],"propose":[141],"retrieval-augmented":[143,194],"strategy.":[144],"Specifically,":[145],"create":[147],"an":[148],"cache":[150,171],"captions":[153],"generated":[154],"large":[157],"(LLM).":[160],"During":[161],"training,":[162],"embeddings":[165,168],"retrieve":[166],"this":[170],"use":[173],"ensuring":[177],"consistent":[178,197],"modalities":[179],"testing":[183],"eliminating":[185],"information":[186],"leakage.":[187],"Extensive":[188],"experiment":[189],"results":[190],"show":[191],"that":[192],"our":[193],"achieves":[196],"notable":[199],"performance":[200],"improvements":[201],"over":[202],"existing":[203],"state-of-the-art":[204],"with":[205],"better":[206],"generalizability.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}