{"id":"https://openalex.org/W4221149441","doi":"https://doi.org/10.21437/interspeech.2022-10127","title":"Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection","display_name":"Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221149441","doi":"https://doi.org/10.21437/interspeech.2022-10127"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10127","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5068022654","display_name":"Hyeonuk Nam","orcid":"https://orcid.org/0000-0002-1169-5640"},"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":"Hyeonuk Nam","raw_affiliation_strings":["Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085633235","display_name":"Seong-Hu Kim","orcid":"https://orcid.org/0000-0003-3101-8732"},"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":"Seong-Hu Kim","raw_affiliation_strings":["Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087819501","display_name":"Byeong-Yun Ko","orcid":"https://orcid.org/0000-0002-8965-8954"},"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":"Byeong-Yun Ko","raw_affiliation_strings":["Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044559850","display_name":"Yong\u2010Hwa Park","orcid":"https://orcid.org/0000-0003-3519-1321"},"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":"Yong-Hwa Park","raw_affiliation_strings":["Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":7.7453,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98457664,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2763","last_page":"2767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9736999869346619,"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":0.7138767242431641},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6776548624038696},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5417500138282776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5159628987312317},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4587659239768982},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4204290211200714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33267107605934143},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10329186916351318},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08589157462120056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138767242431641},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6776548624038696},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5417500138282776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5159628987312317},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4587659239768982},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4204290211200714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33267107605934143},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10329186916351318},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08589157462120056},{"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:10.21437/interspeech.2022-10127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10127","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7164413439","display_name":null,"funder_award_id":"20204030200050","funder_id":"https://openalex.org/F4320335199","funder_display_name":"Korea Institute of Energy Technology Evaluation and Planning"},{"id":"https://openalex.org/G7441292674","display_name":null,"funder_award_id":"20210623","funder_id":"https://openalex.org/F4320322011","funder_display_name":"Ministry of Oceans and Fisheries"}],"funders":[{"id":"https://openalex.org/F4320322011","display_name":"Ministry of Oceans and Fisheries","ror":"https://ror.org/00c5s4a53"},{"id":"https://openalex.org/F4320327222","display_name":"Korea Institute of Marine Science and Technology promotion","ror":null},{"id":"https://openalex.org/F4320335199","display_name":"Korea Institute of Energy Technology Evaluation and Planning","ror":"https://ror.org/02zq38y32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1604034532","https://openalex.org/W2058155398","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2759976799","https://openalex.org/W2765407302","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2953070460","https://openalex.org/W3015190346","https://openalex.org/W3034421924","https://openalex.org/W3094148097","https://openalex.org/W3094502228","https://openalex.org/W3097777922","https://openalex.org/W3180060682","https://openalex.org/W3185974171","https://openalex.org/W3198041020","https://openalex.org/W3203812731","https://openalex.org/W4224324207","https://openalex.org/W4241441202","https://openalex.org/W4288099153","https://openalex.org/W4289029600","https://openalex.org/W4293246336","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4211182446","https://openalex.org/W4245868110","https://openalex.org/W2778699561","https://openalex.org/W4252487970","https://openalex.org/W4255839737","https://openalex.org/W4240941274","https://openalex.org/W2775902113","https://openalex.org/W1971118083","https://openalex.org/W4233773735","https://openalex.org/W4255037941"],"abstract_inverted_index":{"2D":[0,19,45],"convolution":[1,20,46,53,65,109,131],"is":[2,35,110,132],"widely":[3],"used":[4],"in":[5,71,75,134],"sound":[6,17,25,79,118],"event":[7],"detection":[8,80,115],"(SED)":[9],"to":[10,40,59],"recognize":[11],"two":[12],"dimensional":[13],"time-frequency":[14,122],"patterns":[15],"of":[16,44,62,77,98,116],"events.However,":[18],"enforces":[21],"translation":[22],"equivariance":[23],"on":[24,47,90],"events":[26,119],"along":[27],"both":[28],"time":[29],"and":[30,100],"frequency":[31,34,51,60,101,107,129],"axis":[32],"while":[33],"not":[36],"shift-invariant":[37],"dimension.In":[38],"order":[39],"improve":[41],"physical":[42],"consistency":[43],"SED,":[48],"we":[49,104,126],"propose":[50],"dynamic":[52,64,102,108,130],"which":[54],"applies":[55],"kernel":[56],"that":[57,106,128],"adapts":[58],"components":[61],"input.Frequency":[63],"outperforms":[66,85],"the":[67],"baseline":[68,99],"by":[69,93],"6.3%":[70],"DESED":[72],"validation":[73],"dataset":[74],"terms":[76],"polyphonic":[78],"score":[81],"(PSDS).It":[82],"also":[83],"significantly":[84],"other":[86],"pre-existing":[87],"contentadaptive":[88],"methods":[89],"SED.In":[91],"addition,":[92],"comparing":[94],"class-wise":[95],"F1":[96],"scores":[97],"convolution,":[103],"showed":[105],"especially":[111],"more":[112],"effective":[113],"for":[114],"non-stationary":[117],"with":[120],"intricate":[121],"patterns.From":[123],"this":[124],"result,":[125],"verified":[127],"superior":[133],"recognizing":[135],"frequency-dependent":[136],"patterns.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}