{"id":"https://openalex.org/W4283067646","doi":"https://doi.org/10.21437/interspeech.2022-11481","title":"Event-related data conditioning for acoustic event classification","display_name":"Event-related data conditioning for acoustic event classification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283067646","doi":"https://doi.org/10.21437/interspeech.2022-11481"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11481","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11481","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01GMB8RZGTHYXCEXN7VTD7TZ4Z/file/01GMBABKHVNRD1WEJ4103RNG4R.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063248625","display_name":"Yuanbo Hou","orcid":"https://orcid.org/0000-0001-8469-5740"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["WAVES Research Group, Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WAVES Research Group, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069519911","display_name":"Dick Botteldooren","orcid":"https://orcid.org/0000-0002-7756-7238"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dick Botteldooren","raw_affiliation_strings":["WAVES Research Group, Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WAVES Research Group, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1561","last_page":"1565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9975000023841858,"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":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8057186603546143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7539690732955933},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7266142964363098},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6635693311691284},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5609517693519592},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5199831128120422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5010170936584473},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44504687190055847},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4425106346607208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4260202944278717},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4186839163303375},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4126686155796051},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.10225197672843933},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09554848074913025},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08746844530105591}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8057186603546143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539690732955933},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7266142964363098},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6635693311691284},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5609517693519592},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5199831128120422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5010170936584473},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44504687190055847},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4425106346607208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260202944278717},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4186839163303375},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4126686155796051},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.10225197672843933},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09554848074913025},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08746844530105591},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11481","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11481","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"},{"id":"pmh:oai:archive.ugent.be:01GMB8RZGTHYXCEXN7VTD7TZ4Z","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01GMB8RZGTHYXCEXN7VTD7TZ4Z","pdf_url":"https://biblio.ugent.be/publication/01GMB8RZGTHYXCEXN7VTD7TZ4Z/file/01GMBABKHVNRD1WEJ4103RNG4R.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01GMB8RZGTHYXCEXN7VTD7TZ4Z","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01GMB8RZGTHYXCEXN7VTD7TZ4Z","pdf_url":"https://biblio.ugent.be/publication/01GMB8RZGTHYXCEXN7VTD7TZ4Z/file/01GMBABKHVNRD1WEJ4103RNG4R.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4283067646.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2086384421","https://openalex.org/W2157825442","https://openalex.org/W2176625348","https://openalex.org/W2187089797","https://openalex.org/W2306289963","https://openalex.org/W2467206671","https://openalex.org/W2534681680","https://openalex.org/W2592944988","https://openalex.org/W2593116425","https://openalex.org/W2761246525","https://openalex.org/W2775505379","https://openalex.org/W2793307691","https://openalex.org/W2799811907","https://openalex.org/W2886093827","https://openalex.org/W2891168223","https://openalex.org/W2936774411","https://openalex.org/W2954731415","https://openalex.org/W2963022469","https://openalex.org/W2963158330","https://openalex.org/W2964218314","https://openalex.org/W2982106364","https://openalex.org/W3015469592","https://openalex.org/W3015597694","https://openalex.org/W3034600060","https://openalex.org/W3049446265","https://openalex.org/W3095738461","https://openalex.org/W3097059024","https://openalex.org/W3097791920","https://openalex.org/W3110606395","https://openalex.org/W3137384391","https://openalex.org/W3175052625","https://openalex.org/W3185739472","https://openalex.org/W3196974791","https://openalex.org/W4289286846","https://openalex.org/W4289329167","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"Models":[0],"based":[1,145],"on":[2,36,131,146],"diverse":[3],"attention":[4,81,143],"mechanisms":[5],"have":[6],"recently":[7],"shined":[8],"in":[9,23,178],"tasks":[10,25],"related":[11,61],"to":[12,26,50,62,91,138,155],"acoustic":[13,32,63,147],"event":[14,78],"classification":[15],"(AEC).":[16],"Among":[17],"them,":[18],"self-attention":[19,98],"is":[20,137],"often":[21],"used":[22],"audio-only":[24],"help":[27],"the":[28,37,47,71,77,92,109,141,151,157,180,184,202],"model":[29],"recognize":[30],"different":[31],"events.":[33],"Self-attention":[34],"relies":[35],"similarity":[38],"between":[39,111,197],"time":[40,84],"frames,":[41],"and":[42,106,114,149,169,173,183,194,199],"uses":[43],"global":[44,85],"information":[45,60,72,86,154,193],"from":[46],"whole":[48],"segment":[49],"highlight":[51],"specific":[52],"features":[53],"within":[54,73],"a":[55],"frame.":[56,158],"In":[57],"real":[58],"life,":[59],"events":[64,112,198],"will":[65],"attenuate":[66],"over":[67],"time,":[68],"which":[69],"means":[70],"some":[74],"frames":[75],"around":[76],"deserves":[79],"more":[80],"than":[82],"distant":[83],"that":[87,97],"may":[88,99],"be":[89],"unrelated":[90],"event.":[93],"This":[94],"paper":[95,119],"shows":[96],"over-enhance":[100],"certain":[101],"segments":[102],"of":[103,135,204],"audio":[104],"representations,":[105],"smooth":[107],"out":[108],"boundaries":[110,196],"representations":[113],"background":[115],"noises.":[116],"Hence,":[117],"this":[118],"proposes":[120],"an":[121],"event-related":[122,152,191],"data":[123,166],"conditioning":[124],"(EDC)":[125],"for":[126],"AEC.":[127,205],"EDC":[128,136,175,188],"directly":[129],"works":[130],"spectrograms.":[132],"The":[133],"idea":[134],"adaptively":[139],"select":[140],"frame-related":[142],"range":[144],"features,":[148],"gather":[150],"local":[153,192],"represent":[156],"Experiments":[159],"show":[160],"that:":[161],"1)":[162],"compared":[163],"with":[164],"spectrogram-based":[165],"augmentation":[167],"methods":[168],"trainable":[170],"feature":[171],"weighting":[172],"self-attention,":[174],"outperforms":[176],"them":[177],"both":[179],"original-size":[181],"mode":[182],"augmented":[185],"mode;":[186],"2)":[187],"effectively":[189],"gathers":[190],"enhances":[195],"backgrounds,":[200],"improving":[201],"performance":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}