{"id":"https://openalex.org/W4408352228","doi":"https://doi.org/10.1109/icassp49660.2025.10888750","title":"Collision-less and Balanced Sampling for Language-Queried Audio Source Separation","display_name":"Collision-less and Balanced Sampling for Language-Queried Audio Source Separation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352228","doi":"https://doi.org/10.1109/icassp49660.2025.10888750"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888750","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/A5068261641","display_name":"Binh Thien Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Binh Thien Nguyen","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091219538","display_name":"Daisuke Niizumi","orcid":"https://orcid.org/0000-0002-5063-0508"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Niizumi","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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":0.8082350492477417},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5690150856971741},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.5022468566894531},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43840292096138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.31436145305633545},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2691231369972229},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10979074239730835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082350492477417},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5690150856971741},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.5022468566894531},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43840292096138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31436145305633545},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2691231369972229},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10979074239730835},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888750","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338124","display_name":"Strategic International Collaborative Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2148143831","https://openalex.org/W2440599146","https://openalex.org/W2593116425","https://openalex.org/W2938798071","https://openalex.org/W2945761034","https://openalex.org/W2951130829","https://openalex.org/W2988200020","https://openalex.org/W2998657200","https://openalex.org/W3015591594","https://openalex.org/W3160972914","https://openalex.org/W3205743929","https://openalex.org/W4205689591","https://openalex.org/W4224871700","https://openalex.org/W4226151502","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4372260051","https://openalex.org/W4372260310","https://openalex.org/W4387835382","https://openalex.org/W4392903392","https://openalex.org/W4392903555","https://openalex.org/W4394862844","https://openalex.org/W4400033239","https://openalex.org/W4403780823","https://openalex.org/W4404317174","https://openalex.org/W6668990524","https://openalex.org/W6784429643","https://openalex.org/W6847370424","https://openalex.org/W6852871851","https://openalex.org/W6865118152","https://openalex.org/W6869592674","https://openalex.org/W6885143814"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3113932901","https://openalex.org/W4396701345","https://openalex.org/W650625605","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Language-queried":[0],"audio":[1,40,70,177,195],"source":[2],"separation":[3],"(LASS)":[4],"is":[5,81,260],"an":[6,194],"emerging":[7],"research":[8],"field":[9],"that":[10,113,175],"has":[11,56],"recently":[12],"received":[13],"increasing":[14],"attention.":[15],"This":[16],"task":[17],"aims":[18],"to":[19,75,117,225],"isolate":[20],"individual":[21],"sources":[22],"from":[23,140],"a":[24,77,127],"mixture":[25],"of":[26,53,184,229,236,244],"signals":[27,71,171],"using":[28,164,193,208],"natural":[29],"language":[30],"descriptions,":[31],"enabling":[32],"applications":[33],"in":[34,72,97,105,252],"various":[35,69],"areas":[36],"such":[37],"as":[38,84,92],"automatic":[39],"editing.":[41],"While":[42],"conventional":[43],"methods":[44],"focus":[45],"on":[46],"the":[47,50,73,85,88,98,106,115,122,141,169,185,189,200,227,234,242,245],"system":[48],"architecture,":[49],"important":[51],"aspect":[52],"data":[54,60,142,165],"processing":[55],"been":[57],"overlooked.":[58],"The":[59],"for":[61],"training":[62,129,133],"LASS":[63,134,250],"are":[64,90,154,172,191],"typically":[65],"created":[66],"by":[67,163],"mixing":[68],"dataset":[74],"form":[76],"mixture.":[78],"One":[79],"signal":[80,100],"then":[82],"used":[83],"target,":[86],"whereas":[87],"others":[89,153],"regarded":[91],"interference.":[93],"However,":[94],"sound":[95,124,147],"events":[96,125,148],"target":[99,186],"could":[101],"overlap":[102],"with":[103,135,182],"those":[104,183],"interference":[107,170],"signals,":[108],"which":[109],"may":[110,138],"cause":[111],"confusion":[112],"instructs":[114],"model":[116,259],"both":[118],"retain":[119],"and":[120],"suppress":[121],"same":[123],"within":[126],"single":[128],"example.":[130],"In":[131,156],"addition,":[132],"large-scale":[136],"datasets":[137],"suffer":[139],"imbalance":[143],"problem,":[144],"where":[145,188],"some":[146],"appear":[149],"too":[150],"frequently":[151],"while":[152,232],"rare.":[155],"this":[157],"paper,":[158],"we":[159,202,218],"address":[160],"these":[161],"problems":[162],"sampling":[166,206,224],"techniques.":[167],"Specifically,":[168],"sampled":[173],"so":[174],"their":[176,215],"tags":[178,190],"do":[179],"not":[180],"conflict":[181],"signal,":[187],"generated":[192],"tagging":[196],"model.":[197],"To":[198],"balance":[199],"data,":[201],"consider":[203],"several":[204],"balanced":[205],"approaches":[207],"tag":[209],"or":[210,222],"caption":[211],"embedding.":[212],"By":[213],"leveraging":[214],"distribution":[216],"information,":[217],"use":[219],"either":[220],"weighted":[221],"group":[223],"boost":[226],"occurrence":[228],"underrepresented":[230],"samples":[231],"reducing":[233],"presence":[235],"overrepresented":[237],"ones.":[238],"Experimental":[239],"results":[240],"show":[241],"superiority":[243],"proposed":[246],"method":[247],"over":[248],"state-of-the-art":[249],"systems":[251],"DCASE":[253],"2024":[254],"Challenge":[255],"Task":[256],"9.":[257],"Pre-trained":[258],"available":[261],"at:":[262],"https://github.com/tucothien/LASS-CLBS.":[263]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}