{"id":"https://openalex.org/W4408353947","doi":"https://doi.org/10.1109/icassp49660.2025.10889789","title":"Exploring Text-Queried Sound Event Detection with Audio Source Separation","display_name":"Exploring Text-Queried Sound Event Detection with Audio Source Separation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353947","doi":"https://doi.org/10.1109/icassp49660.2025.10889789"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889789","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/A5113113933","display_name":"Han Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Yin","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027263923","display_name":"Jisheng Bai","orcid":"https://orcid.org/0000-0002-9803-8212"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082028932","display_name":"Yang Xiao","orcid":"https://orcid.org/0000-0002-3982-9540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":["Fortemedia,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Fortemedia,Singapore,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460850","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8814-1988"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110651076","display_name":"Shuheng Zheng","orcid":"https://orcid.org/0009-0009-5394-3428"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Alibaba Group,Speech Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003578886","display_name":"Yafeng Chen","orcid":"https://orcid.org/0000-0002-5459-4428"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Fortemedia,Singapore,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686893","display_name":"Chong Deng","orcid":"https://orcid.org/0000-0002-7287-7042"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Deng","raw_affiliation_strings":["Alibaba Group,Speech Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330941","display_name":"Jianfeng Chen","orcid":"https://orcid.org/0000-0002-4182-145X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Chen","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5113113933"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":17.1711,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99409237,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"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":0.9995999932289124,"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/T11309","display_name":"Music 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":0.9771999716758728,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.965499997138977,"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":0.7842278480529785},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.625389814376831},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5335498452186584},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.48543959856033325},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4674355089664459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3828020989894867},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23213890194892883},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13128575682640076},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11162623763084412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842278480529785},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.625389814376831},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5335498452186584},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.48543959856033325},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4674355089664459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3828020989894867},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23213890194892883},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13128575682640076},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11162623763084412},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889789","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":33,"referenced_works":["https://openalex.org/W2079735306","https://openalex.org/W2118230268","https://openalex.org/W2119110418","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2810934215","https://openalex.org/W3015199127","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3124216180","https://openalex.org/W3160845765","https://openalex.org/W3161792602","https://openalex.org/W3161934504","https://openalex.org/W4205689591","https://openalex.org/W4206247269","https://openalex.org/W4221149441","https://openalex.org/W4224871700","https://openalex.org/W4224920041","https://openalex.org/W4315926819","https://openalex.org/W4372260310","https://openalex.org/W4375869216","https://openalex.org/W4387185347","https://openalex.org/W4400033239","https://openalex.org/W4400350361","https://openalex.org/W4401610131","https://openalex.org/W4403780823","https://openalex.org/W4409346508","https://openalex.org/W6869592674","https://openalex.org/W6869853846","https://openalex.org/W6870174606","https://openalex.org/W6870977964","https://openalex.org/W6885143814"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3112881379","https://openalex.org/W2167133075","https://openalex.org/W2019256813","https://openalex.org/W2132877328","https://openalex.org/W2002298560","https://openalex.org/W3144741696"],"abstract_inverted_index":{"In":[0],"sound":[1,6],"event":[2],"detection":[3,28],"(SED),":[4],"overlapping":[5],"events":[7,14,60],"pose":[8],"a":[9,45,78,103],"significant":[10],"challenge,":[11],"as":[12,117],"certain":[13],"can":[15,143],"be":[16],"easily":[17],"masked":[18],"by":[19],"background":[20],"noise":[21],"or":[22],"other":[23],"events,":[24],"resulting":[25],"in":[26,85,124],"poor":[27],"performance.":[29],"To":[30,98],"address":[31,99],"this":[32,115],"issue,":[33],"we":[34,42,101,162],"propose":[35],"the":[36,54,62,110,121,146,158,168],"text-queried":[37],"SED":[38,68,147],"(TQ-SED)":[39],"framework.":[40,160],"Specifically,":[41],"first":[43,122],"pre-train":[44],"language-queried":[46,130],"audio":[47,55,88,131],"source":[48,132,174],"separation":[49,133],"(LASS)":[50],"model":[51,136,171,178],"to":[52,58,72,114,166],"separate":[53],"tracks":[56],"corresponding":[57],"different":[59],"from":[61],"input":[63],"audio.":[64],"Then,":[65],"multiple":[66],"target":[67],"branches":[69],"are":[70,179],"employed":[71],"detect":[73],"individual":[74],"events.":[75],"AudioSep":[76],"is":[77],"state-of-the-art":[79],"LASS":[80],"model,":[81],"but":[82],"has":[83],"limitations":[84],"extracting":[86],"dynamic":[87],"information":[89],"because":[90],"of":[91,152,170],"its":[92],"pure":[93],"convolutional":[94],"structure":[95,116],"for":[96],"separation.":[97],"this,":[100],"integrate":[102],"dual-path":[104],"recurrent":[105],"neural":[106],"network":[107],"block":[108],"into":[109],"model.":[111],"We":[112],"refer":[113],"AudioSep-DP,":[118],"which":[119],"achieves":[120],"place":[123],"DCASE":[125],"2024":[126],"Task":[127],"9":[128],"on":[129,154],"(objective":[134],"single":[135],"track).":[137],"Experimental":[138],"results":[139],"show":[140],"that":[141],"TQ-SED":[142],"significantly":[144],"improve":[145],"performance,":[148],"with":[149],"an":[150],"improvement":[151],"7.22%":[153],"F1":[155],"score":[156],"over":[157],"conventional":[159],"Additionally,":[161],"setup":[163],"comprehensive":[164],"experiments":[165],"explore":[167],"impact":[169],"complexity.":[172],"The":[173],"code":[175],"and":[176],"pre-trained":[177],"released":[180],"at":[181],"https://github.com/apple-yinhan/TQ-SED.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
