{"id":"https://openalex.org/W4408353470","doi":"https://doi.org/10.1109/icassp49660.2025.10889813","title":"FAF-Filt: Frequency-aware Fourier Filter for Sound Event Detection","display_name":"FAF-Filt: Frequency-aware Fourier Filter for Sound Event Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353470","doi":"https://doi.org/10.1109/icassp49660.2025.10889813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889813","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/A5028556500","display_name":"Siyu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Siyu Sun","raw_affiliation_strings":["ByteDance China,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009836479","display_name":"Xiaohuai Le","orcid":"https://orcid.org/0000-0002-6419-1825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohuai Le","raw_affiliation_strings":["ByteDance China,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071017867","display_name":"Zhuangqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuangqi Chen","raw_affiliation_strings":["ByteDance China,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091584895","display_name":"Xianjun Xia","orcid":"https://orcid.org/0000-0001-5277-6634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["ByteDance China,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China,Shenzhen,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018343941","display_name":"Chuanzeng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanzeng Huang","raw_affiliation_strings":["ByteDance China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance China,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028556500"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87104211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9958000183105469,"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":0.9815000295639038,"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":0.6210708022117615},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4654653072357178},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4362805187702179},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4265595078468323},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42476335167884827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3283325731754303},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16486334800720215},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07392820715904236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210708022117615},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4654653072357178},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4362805187702179},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4265595078468323},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42476335167884827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3283325731754303},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16486334800720215},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07392820715904236},{"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/icassp49660.2025.10889813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889813","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":24,"referenced_works":["https://openalex.org/W2591013610","https://openalex.org/W2752782242","https://openalex.org/W2959539607","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3034421924","https://openalex.org/W3178592608","https://openalex.org/W3198041020","https://openalex.org/W3199003182","https://openalex.org/W3203468141","https://openalex.org/W4221149441","https://openalex.org/W4225331914","https://openalex.org/W4296068754","https://openalex.org/W4372260471","https://openalex.org/W4375839990","https://openalex.org/W4375868802","https://openalex.org/W4384702789","https://openalex.org/W4392909508","https://openalex.org/W4402112391","https://openalex.org/W6733814495","https://openalex.org/W6761305474","https://openalex.org/W6785302134","https://openalex.org/W6797578546","https://openalex.org/W6843259600"],"related_works":["https://openalex.org/W2043727559","https://openalex.org/W2031453039","https://openalex.org/W2899315007","https://openalex.org/W2549138563","https://openalex.org/W2335010068","https://openalex.org/W1969976809","https://openalex.org/W4376623368","https://openalex.org/W2035889111","https://openalex.org/W4386768751","https://openalex.org/W4241891915"],"abstract_inverted_index":{"Capturing":[0],"time-frequency":[1],"patterns":[2],"along":[3],"the":[4,10,48,69,80,104,111,116,121,128],"frequency":[5,70,92],"axis,":[6],"is":[7,99],"crucial":[8],"for":[9],"precision":[11],"of":[12,24,107,120,127,138],"sound":[13,140],"event":[14,141],"detection":[15],"systems.":[16],"Frequency":[17],"dynamic":[18],"convolution":[19,97],"(FDY)":[20],"and":[21,54,72,118],"a":[22,62,74,145],"series":[23],"its":[25],"variants":[26],"which":[27,60,109],"incorporate":[28],"frequency-adaptive":[29,96],"kernels":[30],"in":[31,136,149],"standard":[32],"2D":[33,63],"convolutions,":[34],"have":[35],"demonstrated":[36],"remarkable":[37],"performance,":[38],"yet":[39],"also":[40],"suffered":[41],"from":[42],"high":[43],"computational":[44],"costs.":[45],"To":[46],"address":[47],"issue,":[49],"we":[50],"propose":[51],"an":[52],"efficient":[53],"light-weighted":[55],"frequency-aware":[56,76,112],"Fourier":[57,64],"filter":[58,77],"(FAF-Filt),":[59],"performs":[61],"transform":[65],"on":[66],"features":[67],"to":[68,78,89,101],"domain":[71],"employs":[73],"learnable":[75],"process":[79],"transformed":[81],"features,":[82],"thereby":[83],"integrating":[84],"global":[85],"information":[86],"more":[87],"effectively":[88],"extract":[90],"decisive":[91],"components.":[93],"In":[94],"addition,":[95],"(FA-Conv)":[98],"adopted":[100],"further":[102],"strengthen":[103],"representative":[105],"ability":[106],"convolution,":[108],"incorporates":[110],"attention":[113],"mechanism":[114],"into":[115],"inputs":[117],"outputs":[119],"convolutions.":[122],"Experimental":[123],"results":[124],"exhibit":[125],"superiority":[126],"proposed":[129],"method,":[130],"achieving":[131],"comparable":[132],"performance":[133],"with":[134,144],"FDY-CRNN":[135],"terms":[137],"polyphonic":[139],"scores":[142],"(PSDS)":[143],"significantly":[146],"56%":[147],"reduction":[148],"parameters.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}