{"id":"https://openalex.org/W4224871700","doi":"https://doi.org/10.21437/interspeech.2022-10894","title":"Separate What You Describe: Language-Queried Audio Source Separation","display_name":"Separate What You Describe: Language-Queried Audio Source Separation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224871700","doi":"https://doi.org/10.21437/interspeech.2022-10894"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10894","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10894","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhao Mei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057816329","display_name":"Jinzheng Zhao","orcid":"https://orcid.org/0009-0004-3910-850X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinzheng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116239819","display_name":"Qiushi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiushi Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1801","last_page":"1805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.870956540107727},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6387025713920593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5480046272277832},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48121240735054016},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4620600938796997},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46103644371032715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.456811785697937},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42380568385124207},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.419761061668396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37163692712783813},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13681307435035706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870956540107727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6387025713920593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5480046272277832},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48121240735054016},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4620600938796997},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46103644371032715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.456811785697937},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42380568385124207},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.419761061668396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37163692712783813},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13681307435035706},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10894","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10894","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"In":[0],"this":[1,67],"paper,":[2],"we":[3,69,130],"introduce":[4],"the":[5,31,52,62,88,95,104,115],"task":[6],"of":[7,30,54,106],"language-queried":[8],"audio":[9,22,63,100,154],"source":[10,19,33,90,157],"separation":[11],"(LASS),":[12],"which":[13],"aims":[14],"to":[15,79],"separate":[16,87],"a":[17,26,38,111],"target":[18,32,89],"from":[20,98,114],"an":[21,72,99],"mixture":[23],"based":[24],"on":[25],"natural":[27,55],"language":[28,56,96],"query":[29,97],"(e.g.,":[34],"\"a":[35],"man":[36],"tells":[37],"joke":[39],"followed":[40],"by":[41],"people":[42],"laughing\").":[43],"A":[44],"unique":[45],"challenge":[46],"in":[47,149],"LASS":[48],"is":[49,77,92],"associated":[50],"with":[51,61,94,110],"complexity":[53],"description":[57],"and":[58,83,86,156],"its":[59,146],"relation":[60],"sources.":[64],"To":[65],"address":[66],"issue,":[68],"proposed":[70,108],"LASS-Net,":[71],"end-to-end":[73],"neural":[74],"network":[75],"that":[76,91,121,132],"learned":[78],"jointly":[80],"process":[81],"acoustic":[82],"linguistic":[84],"information,":[85],"consistent":[93],"mixture.":[101],"We":[102],"evaluate":[103],"performance":[105],"our":[107],"system":[109],"dataset":[112],"created":[113],"AudioCaps":[116],"dataset.":[117],"Experimental":[118],"results":[119,137],"show":[120],"LASS-Net":[122,133],"achieves":[123,134],"considerable":[124],"improvements":[125],"over":[126],"baseline":[127],"methods.":[128],"Furthermore,":[129],"observe":[131],"promising":[135],"generalization":[136],"when":[138],"using":[139],"diverse":[140],"human-annotated":[141],"descriptions":[142],"as":[143],"queries,":[144],"indicating":[145],"potential":[147],"use":[148],"real-world":[150],"scenarios.":[151],"The":[152],"separated":[153],"samples":[155],"code":[158],"are":[159],"available":[160],"at":[161],"https://liuxubo717.github.io/LASS-demopage.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}