{"id":"https://openalex.org/W4408354856","doi":"https://doi.org/10.1109/icassp49660.2025.10888414","title":"Formula-Supervised Sound Event Detection: Pre-Training Without Real Data","display_name":"Formula-Supervised Sound Event Detection: Pre-Training Without Real Data","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354856","doi":"https://doi.org/10.1109/icassp49660.2025.10888414"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888414","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/A5103148125","display_name":"Yuto Shibata","orcid":"https://orcid.org/0009-0003-0517-5600"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuto Shibata","raw_affiliation_strings":["Keio University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085731517","display_name":"Keitaro Tanaka","orcid":"https://orcid.org/0009-0005-4338-5224"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keitaro Tanaka","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594529","display_name":"Hirokatsu Kalaoka","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokatsu Kalaoka","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Keio University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72495327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.984000027179718,"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/T10860","display_name":"Speech and Audio Processing","score":0.9837999939918518,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7319359183311462},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6841564178466797},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5547074675559998},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5003082752227783},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4737181067466736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580700397491455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41769173741340637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36334240436553955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32492053508758545},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11957418918609619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319359183311462},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6841564178466797},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5547074675559998},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5003082752227783},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4737181067466736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580700397491455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41769173741340637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36334240436553955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32492053508758545},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11957418918609619},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"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/icassp49660.2025.10888414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888414","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":35,"referenced_works":["https://openalex.org/W2088432713","https://openalex.org/W2135342008","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2771361008","https://openalex.org/W2936774411","https://openalex.org/W2959539607","https://openalex.org/W2962910554","https://openalex.org/W2963723765","https://openalex.org/W2985693847","https://openalex.org/W3015190346","https://openalex.org/W3090054208","https://openalex.org/W3112788634","https://openalex.org/W3137182587","https://openalex.org/W3162999565","https://openalex.org/W3178592608","https://openalex.org/W3196974791","https://openalex.org/W3200431187","https://openalex.org/W4212848528","https://openalex.org/W4230506641","https://openalex.org/W4307823382","https://openalex.org/W4313013151","https://openalex.org/W4372263379","https://openalex.org/W4386075850","https://openalex.org/W4390872644","https://openalex.org/W4392904244","https://openalex.org/W4392931295","https://openalex.org/W4404600560","https://openalex.org/W6639003370","https://openalex.org/W6733814495","https://openalex.org/W6753516609","https://openalex.org/W6771763809","https://openalex.org/W6848208918","https://openalex.org/W6852791012"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W3216976533","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,29,97],"propose":[4,98],"a":[5,63,99,105],"novel":[6,100],"formula-driven":[7,26],"supervised":[8],"learning":[9],"(FDSL)":[10],"framework":[11],"for":[12,37,169],"pre-training":[13,124,149],"an":[14],"environmental":[15],"sound":[16,38,53],"analysis":[17],"model":[18,154],"by":[19,58,87,125,161],"leveraging":[20],"acoustic":[21,110],"signals":[22],"parametrically":[23],"synthesized":[24],"through":[25],"methods.":[27],"Specifically,":[28],"outline":[30],"detailed":[31],"procedures":[32],"and":[33,50,83,143,156],"evaluate":[34],"their":[35],"effectiveness":[36],"event":[39],"detection":[40],"(SED).":[41],"The":[42,119,174],"SED":[43],"task,":[44],"which":[45],"involves":[46],"estimating":[47],"the":[48,59,88,127,165],"types":[49],"timings":[51],"of":[52,61,66,91],"events,":[54],"is":[55,73,177],"particularly":[56],"challenged":[57],"difficulty":[60],"acquiring":[62],"sufficient":[64],"quantity":[65],"accurately":[67],"labeled":[68],"training":[69],"data.":[70],"Moreover,":[71],"it":[72],"well":[74],"known":[75],"that":[76,103,147],"manually":[77],"annotated":[78],"labels":[79],"often":[80],"contain":[81],"noises":[82],"are":[84,112],"significantly":[85,152],"influenced":[86],"subjective":[89],"judgment":[90],"annotators.":[92],"To":[93],"address":[94],"these":[95],"challenges,":[96],"pretraining":[101],"method":[102,121],"utilizes":[104],"synthetic":[106],"dataset,":[107],"Formula-SED,":[108],"where":[109],"data":[111],"generated":[113],"solely":[114],"based":[115],"on":[116],"mathematical":[117],"formulas.":[118],"proposed":[120],"enables":[122],"large-scale":[123,148],"using":[126],"synthesis":[128],"parameters":[129],"applied":[130],"at":[131,178],"each":[132],"time":[133],"step":[134],"as":[135,159],"ground":[136],"truth":[137],"labels,":[138],"thereby":[139],"eliminating":[140],"label":[141],"noise":[142],"bias.":[144],"We":[145],"demonstrate":[146],"with":[150],"Formula-SED":[151],"enhances":[153],"accuracy":[155],"accelerates":[157],"training,":[158],"evidenced":[160],"our":[162],"results":[163],"in":[164],"DESED":[166],"dataset":[167],"used":[168],"DCASE2023":[170],"Challenge":[171],"Task":[172],"4.":[173],"project":[175],"page":[176],"https://yutoshibata07.github.io/Formula-SED/.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}