{"id":"https://openalex.org/W4408351785","doi":"https://doi.org/10.1109/icassp49660.2025.10890066","title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","display_name":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351785","doi":"https://doi.org/10.1109/icassp49660.2025.10890066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890066","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":"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/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067198078","display_name":"Yen-Ju Lu","orcid":"https://orcid.org/0000-0001-8400-4188"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078637653","display_name":"Karan Thakkar","orcid":"https://orcid.org/0000-0002-6803-1116"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Thakkar","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101664824"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":9.7513,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98266191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9926999807357788,"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":0.9916999936103821,"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":0.6522171497344971},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5339775085449219},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4474918842315674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4010744094848633},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19719693064689636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1702222228050232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07258692383766174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6522171497344971},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5339775085449219},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4474918842315674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4010744094848633},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19719693064689636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1702222228050232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07258692383766174},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890066","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2988200020","https://openalex.org/W3015371781","https://openalex.org/W3037038648","https://openalex.org/W3094550259","https://openalex.org/W3095263845","https://openalex.org/W3160972914","https://openalex.org/W3197762568","https://openalex.org/W4224914418","https://openalex.org/W4310873168","https://openalex.org/W4372260051","https://openalex.org/W4372260310","https://openalex.org/W4372348953","https://openalex.org/W4375869340","https://openalex.org/W4385822449","https://openalex.org/W4386047807","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4392903103","https://openalex.org/W4392904475","https://openalex.org/W4402112289","https://openalex.org/W4403653559","https://openalex.org/W6746278845","https://openalex.org/W6752516136","https://openalex.org/W6779823529","https://openalex.org/W6848854281","https://openalex.org/W6849109464","https://openalex.org/W6849737538","https://openalex.org/W6853515095","https://openalex.org/W6855917767","https://openalex.org/W6861353174","https://openalex.org/W6873434847"],"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/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,81],"paper,":[2],"we":[3],"introduce":[4],"SoloAudio,":[5],"a":[6,30,47],"novel":[7],"diffusion-based":[8],"generative":[9],"model":[10,49],"for":[11,54,67],"target":[12,55],"sound":[13,77],"extraction":[14],"(TSE).":[15],"Our":[16],"approach":[17,82],"trains":[18],"latent":[19,36],"diffusion":[20],"models":[21,66],"on":[22,35,83,101],"audio,":[23],"replacing":[24],"the":[25,51,84,98],"previous":[26],"U-Net":[27],"backbone":[28],"with":[29],"skip-connected":[31],"Transformer":[32],"that":[33],"operates":[34],"features.":[37],"SoloAudio":[38,58,96],"supports":[39],"both":[40,102],"audio-oriented":[41],"and":[42,75,90,104,107,111,118],"language-oriented":[43],"TSE":[44],"by":[45,63],"utilizing":[46],"CLAP":[48],"as":[50],"feature":[52],"extractor":[53],"sounds.":[56],"Furthermore,":[57],"leverages":[59],"synthetic":[60],"audio":[61],"generated":[62],"state-of-the-art":[64,99],"text-to-audio":[65],"training,":[68],"demonstrating":[69],"strong":[70],"generalization":[71],"to":[72],"out-of-domain":[73,105],"data":[74,92],"unseen":[76],"events.":[78],"We":[79],"evaluate":[80],"FSD":[85],"Kaggle":[86],"2018":[87],"mixture":[88],"dataset":[89],"real":[91],"from":[93],"AudioSet,":[94],"where":[95],"achieves":[97],"results":[100],"in-domain":[103],"data,":[106],"exhibits":[108],"impressive":[109],"zero-shot":[110],"few-shot":[112],"capabilities.":[113],"Source":[114],"code<sup":[115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116,120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[117],"demos<sup":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[121],"are":[122],"released.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}