{"id":"https://openalex.org/W4408352373","doi":"https://doi.org/10.1109/icassp49660.2025.10888769","title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","display_name":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352373","doi":"https://doi.org/10.1109/icassp49660.2025.10888769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888769","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/A5079146015","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594330","display_name":"Gordon Wiehern","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wiehern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90521902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.989799976348877,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9628999829292297,"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":0.8330993056297302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4135803282260895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330993056297302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4135803282260895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888769","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2964058413","https://openalex.org/W2973062255","https://openalex.org/W3015199127","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3095263845","https://openalex.org/W3097777922","https://openalex.org/W3163652268","https://openalex.org/W3175593095","https://openalex.org/W4224871700","https://openalex.org/W4297841626","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385567053","https://openalex.org/W4385822289","https://openalex.org/W4392903801","https://openalex.org/W4392909554","https://openalex.org/W4403126475","https://openalex.org/W4404317174","https://openalex.org/W6746023985","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6810452849","https://openalex.org/W6847370424","https://openalex.org/W6849109464","https://openalex.org/W6855917767","https://openalex.org/W6869592674"],"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":{"The":[0,117],"goal":[1],"of":[2,37,43],"text-queried":[3,68,217],"target":[4],"sound":[5,15],"extraction":[6],"(TSE)":[7],"is":[8,24,84,199],"to":[9,26,29,33,59,71,81,85,130,163,165,172,215],"extract":[10],"from":[11,113],"a":[12,14,19,35,87,101,106],"mixture":[13],"source":[16],"specified":[17],"with":[18,196],"natural-language":[20],"caption.":[21],"While":[22,134],"it":[23],"preferable":[25],"have":[27,155],"access":[28],"large-scale":[30],"text-audio":[31,46],"pairs":[32,47],"address":[34],"variety":[36],"text":[38,123,132,143,204],"queries,":[39],"the":[40,49,67,75,94,114,131,140,153,160],"limited":[41],"number":[42],"available":[44],"high-quality":[45],"hinders":[48],"data":[50,62,76,195,210],"scaling.":[51],"To":[52],"this":[53,55,135,187],"end,":[54],"work":[56,138],"explores":[57],"how":[58],"leverage":[60],"audio-only":[61,194,209],"without":[63],"any":[64],"captions":[65,205],"for":[66],"TSE":[69,107,118,161,218],"task":[70],"potentially":[72],"scale":[73],"up":[74],"amount.":[77],"A":[78],"straightforward":[79],"way":[80],"do":[82],"so":[83],"use":[86],"joint":[88],"audio-text":[89],"embedding":[90,144,197],"model,":[91,99],"such":[92,181],"as":[93,100,182,200,202],"contrastive":[95],"language-audio":[96],"pre-training":[97],"(CLAP)":[98],"query":[102],"encoder":[103],"and":[104,142,175,208],"train":[105],"model":[108,119,162],"using":[109,193,203],"audio":[110,141,166],"embeddings":[111,154],"obtained":[112],"ground-truth":[115],"audio.":[116],"can":[120,184,211],"then":[121],"accept":[122],"queries":[124],"at":[125],"inference":[126],"time":[127],"by":[128],"switching":[129],"encoder.":[133],"approach":[136],"should":[137],"if":[139],"spaces":[145],"in":[146,151],"CLAP":[147],"were":[148],"well":[149],"aligned,":[150],"practice,":[152],"domain-specific":[156],"information":[157],"that":[158,177,192],"causes":[159],"overfit":[164],"queries.":[167],"We":[168],"investigate":[169],"several":[170],"methods":[171,180],"avoid":[173],"overfitting":[174],"show":[176],"simple":[178],"embedding-manipulation":[179],"dropout":[183,198],"effectively":[185,213],"alleviate":[186],"issue.":[188],"Extensive":[189],"experiments":[190],"demonstrate":[191],"effective":[201],"during":[206],"training,":[207],"be":[212],"leveraged":[214],"improve":[216],"models.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}