{"id":"https://openalex.org/W7125020466","doi":"https://doi.org/10.1109/access.2026.3656219","title":"CLAPMamba: CLAP-Guided Mamba for Language-Queried Target Sound Extraction","display_name":"CLAPMamba: CLAP-Guided Mamba for Language-Queried Target Sound Extraction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125020466","doi":"https://doi.org/10.1109/access.2026.3656219"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3656219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656219","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3656219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103791386","display_name":"Jeong Yeol Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong Yeol Yang","raw_affiliation_strings":["School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-6828-4355","affiliations":[{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110752","display_name":"Hyun Joon Park","orcid":"https://orcid.org/0000-0002-5308-6675"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Joon Park","raw_affiliation_strings":["School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5308-6675","affiliations":[{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020828170","display_name":"S. Lee","orcid":"https://orcid.org/0000-0003-1729-1775"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyoung Lee","raw_affiliation_strings":["School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100546978","display_name":"S. Han","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Won Han","raw_affiliation_strings":["School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0040-3542","affiliations":[{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103791386"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.115062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"17182","last_page":"17195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.487199991941452,"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":0.487199991941452,"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":0.4101000130176544,"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":0.06539999693632126,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6517000198364258},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4429999887943268},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.40139999985694885},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3555999994277954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34299999475479126},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6517000198364258},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147999882698059},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.40139999985694885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2831999957561493},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3656219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656219","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6dd2cb6a53724ee8aa1ba8456d7f6696","is_oa":true,"landing_page_url":"https://doaj.org/article/6dd2cb6a53724ee8aa1ba8456d7f6696","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 17182-17195 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3656219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3656219","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2796571515","https://openalex.org/W2936774411","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2998657200","https://openalex.org/W3095263845","https://openalex.org/W3134695619","https://openalex.org/W3138516171","https://openalex.org/W4224871700","https://openalex.org/W4226151502","https://openalex.org/W4226442948","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4372260310","https://openalex.org/W4372348953","https://openalex.org/W4375928773","https://openalex.org/W4385245566","https://openalex.org/W4386764084","https://openalex.org/W4392903216","https://openalex.org/W4393321377","https://openalex.org/W4399939359","https://openalex.org/W4402111418","https://openalex.org/W4402112008","https://openalex.org/W4402112499","https://openalex.org/W4403511013","https://openalex.org/W4404317174","https://openalex.org/W4404586723","https://openalex.org/W4405934446","https://openalex.org/W4406461253","https://openalex.org/W4406461266","https://openalex.org/W4408352482","https://openalex.org/W4408353280","https://openalex.org/W4408353573","https://openalex.org/W4408354310","https://openalex.org/W4408355634","https://openalex.org/W4409157887","https://openalex.org/W4410087476","https://openalex.org/W4413146579"],"related_works":[],"abstract_inverted_index":{"The":[0],"extraction":[1,28],"of":[2,9,47,89,155,204],"particular":[3],"sounds":[4],"from":[5],"noisy,":[6],"overlapping":[7],"mixtures":[8],"audio":[10,69,119],"signals":[11],"remains":[12],"a":[13,72,98,132,143,163],"significant":[14],"practical":[15],"challenge.":[16],"Universal":[17],"separation":[18,268],"is":[19,85,148],"computationally":[20],"intractable":[21],"in":[22,71,246,252],"modern":[23],"real-world":[24],"situations,":[25],"with":[26,157,270],"query-conditioned":[27],"emerging":[29],"as":[30,228],"an":[31,271],"indispensable":[32],"targeted":[33],"approach.":[34],"Among":[35],"conditioning":[36,103,116,135,245],"signals,":[37],"natural":[38],"language":[39],"exhibits":[40,257],"the":[41,45,107,122,152,249,255],"greatest":[42],"expressivity,":[43],"enabling":[44],"specification":[46],"objects,":[48],"attributes,":[49],"and":[50,121,174,183,198,208,216,218,233,248,262,265,277],"relations":[51],"without":[52,75],"auxiliary":[53],"references.":[54],"Although":[55],"existing":[56],"contrastive":[57],"language-audio":[58,63],"pre-training":[59],"(CLAP)-based":[60],"models":[61],"enhance":[62],"alignment,":[64],"they":[65],"typically":[66],"process":[67],"hierarchical":[68,139],"features":[70],"layer-wise":[73],"manner":[74],"modeling":[76,160],"their":[77,82],"semantic":[78,226],"flow":[79],"explicitly.":[80],"Thus,":[81],"computational":[83,108],"cost":[84],"identical":[86],"to":[87,130,150],"that":[88,101,137],"Transformer":[90,189],"blocks.":[91],"In":[92,111,141],"this":[93],"paper,":[94],"we":[95],"introduce":[96],"CLAPMamba,":[97],"hybrid":[99],"architecture":[100],"enhances":[102],"performance":[104],"while":[105,191,212],"reducing":[106],"overhead":[109],"simultaneously.":[110],"QueryNet,":[112],"text":[113],"embeddings":[114],"enable":[115],"for":[117,274],"CLAP":[118],"features,":[120],"Mamba":[123,144],"integration":[124],"stage":[125],"treats":[126],"layer":[127],"outputs":[128],"sequentially":[129],"produce":[131],"single,":[133],"structured":[134],"vector":[136],"preserves":[138],"semantics.":[140],"SeparationNet,":[142],"Forward-Attention":[145],"Block":[146],"(MFAB)":[147],"used":[149],"combine":[151],"global":[153],"context":[154],"self-attention":[156],"linear-time":[158],"sequence":[159,263],"based":[161,242],"on":[162,172,176,243],"bidirectional":[164],"Mamba,":[165],"capturing":[166],"long-range":[167],"dependencies":[168],"more":[169],"efficiently.":[170],"Trained":[171],"AudioCaps":[173],"evaluated":[175],"multiple":[177],"datasets,":[178],"including":[179],"AudioSet,":[180],"ESC-50,":[181],"FSDKaggle2018,":[182],"MUSIC21,":[184],"CLAPMamba":[185],"matches":[186],"or":[187],"outperforms":[188],"baselines":[190],"incurring":[192],"lower":[193,220],"resource":[194],"costs.":[195],"Its":[196],"SDRi":[197],"SI-SDRi":[199],"are":[200],"higher":[201],"than":[202],"those":[203],"CLAPSep":[205],"by":[206,230],"0.25\u20130.46":[207],"0.09\u20130.85":[209],"dB,":[210],"respectively,":[211],"using":[213],"fewer":[214],"parameters":[215],"MACs":[217],"exhibiting":[219],"inference":[221],"latency.":[222],"Moreover,":[223],"it":[224],"increases":[225],"consistency,":[227],"reflected":[229],"text\u2013audio":[231],"similarity":[232],"layerwise":[234],"alignment":[235],"analyses.":[236],"Ablation":[237],"studies":[238],"indicate":[239],"complementary":[240],"improvements":[241],"Mamba-based":[244],"QueryNet":[247],"forward-attention":[250],"module":[251],"SeparationNet.":[253],"Overall,":[254],"method":[256],"high":[258],"generalizability":[259],"across":[260],"datasets":[261],"lengths,":[264],"achieves":[266],"consistent":[267],"quality":[269],"efficiency":[272],"suitable":[273],"on-device":[275],"scenarios":[276],"latency-sensitive":[278],"applications.":[279]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-01-21T00:00:00"}