{"id":"https://openalex.org/W4408346004","doi":"https://doi.org/10.1109/icassp49660.2025.10890645","title":"SoundCollage: Automated Discovery of New Classes in Audio Datasets","display_name":"SoundCollage: Automated Discovery of New Classes in Audio Datasets","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408346004","doi":"https://doi.org/10.1109/icassp49660.2025.10890645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890645","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/A5114634052","display_name":"Ryuhaerang Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Ryuhaerang Choi","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041930081","display_name":"Soumyajit Chatterjee","orcid":"https://orcid.org/0000-0001-5604-2267"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Soumyajit Chatterjee","raw_affiliation_strings":["Nokia Bell Labs,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs,Cambridge,UK","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030362528","display_name":"Dimitris Spathis","orcid":"https://orcid.org/0000-0001-9761-951X"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitris Spathis","raw_affiliation_strings":["Nokia Bell Labs,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs,Cambridge,UK","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101948265","display_name":"Sung-Ju Lee","orcid":"https://orcid.org/0000-0002-5518-2126"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Ju Lee","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053438231","display_name":"Fahim Kawsar","orcid":"https://orcid.org/0000-0001-5057-9557"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fahim Kawsar","raw_affiliation_strings":["Nokia Bell Labs,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs,Cambridge,UK","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062266544","display_name":"Mohammad Malekzadeh","orcid":"https://orcid.org/0000-0002-4247-906X"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohammad Malekzadeh","raw_affiliation_strings":["Nokia Bell Labs,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs,Cambridge,UK","institution_ids":["https://openalex.org/I4210098141"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114634052"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04914504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9544000029563904,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.777400016784668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3347289562225342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3210526406764984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777400016784668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3347289562225342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3210526406764984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890645","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":25,"referenced_works":["https://openalex.org/W1558911006","https://openalex.org/W2593116425","https://openalex.org/W2963518130","https://openalex.org/W2990604239","https://openalex.org/W3031554797","https://openalex.org/W3162220931","https://openalex.org/W3207911573","https://openalex.org/W4205689591","https://openalex.org/W4226033575","https://openalex.org/W4285280787","https://openalex.org/W4387090714","https://openalex.org/W4391865211","https://openalex.org/W4392909683","https://openalex.org/W4392909877","https://openalex.org/W6697668227","https://openalex.org/W6698187734","https://openalex.org/W6745901624","https://openalex.org/W6747728645","https://openalex.org/W6771599870","https://openalex.org/W6779144108","https://openalex.org/W6789998391","https://openalex.org/W6801976681","https://openalex.org/W6846798302","https://openalex.org/W6856434366","https://openalex.org/W6858921003"],"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":{"Developing":[0],"new":[1,10,24,33,81],"machine":[2],"learning":[3],"applications":[4],"often":[5],"requires":[6],"the":[7,61,67,72,75,88,104,116],"collection":[8],"of":[9,74,90,118],"datasets.":[11],"However,":[12],"existing":[13],"datasets":[14,37,122],"may":[15],"already":[16],"contain":[17],"relevant":[18],"information":[19],"to":[20,31,45,59,70,108],"train":[21],"models":[22],"for":[23,78],"purposes.":[25],"We":[26],"propose":[27],"SoundCollage:":[28],"a":[29,99],"framework":[30],"discover":[32],"classes":[34,77],"within":[35,94],"audio":[36,42,50,92],"by":[38,106,124],"incorporating":[39],"(1)":[40],"an":[41,54],"pre-processing":[43],"pipeline":[44],"decompose":[46],"different":[47],"sounds":[48],"in":[49,120,134],"samples,":[51],"and":[52,98,110],"(2)":[53],"automated":[55],"model-based":[56],"annotation":[57],"mechanism":[58],"identify":[60],"discovered":[62,76,95,128],"classes.":[63,129],"Furthermore,":[64],"we":[65,137],"introduce":[66],"clarity":[68],"measure":[69],"assess":[71],"coherence":[73],"better":[79],"training":[80],"downstream":[82,91],"applications.":[83],"Our":[84],"evaluations":[85],"show":[86],"that":[87],"accuracy":[89],"classifiers":[93],"class":[96],"samples":[97],"held-out":[100],"dataset":[101],"improves":[102],"over":[103],"baseline":[105],"up":[107],"34.7%":[109],"4.5%,":[111],"respectively.":[112],"These":[113],"results":[114],"highlight":[115],"potential":[117],"SoundCollage":[119],"making":[121],"reusable":[123],"labeling":[125],"with":[126],"newly":[127],"To":[130],"encourage":[131],"further":[132],"research":[133],"this":[135],"area,":[136],"open-source":[138],"our":[139],"code":[140],"at":[141],"github.com/nokia-bell-labs/audio-class-discovery.":[142]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}