{"id":"https://openalex.org/W4392904167","doi":"https://doi.org/10.1109/icassp48485.2024.10445742","title":"Cross-Triggering Issue in Audio Event Detection and Mitigation","display_name":"Cross-Triggering Issue in Audio Event Detection and Mitigation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904167","doi":"https://doi.org/10.1109/icassp48485.2024.10445742"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081897616","display_name":"Byeonggeun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byeonggeun Kim","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775198","display_name":"Vu Nguyen","orcid":"https://orcid.org/0000-0002-0294-4561"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vu Nguyen","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178977","display_name":"Andrew Bydlon","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Bydlon","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingming Tang","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407094","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-0906-445X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon,Cambridge,MA,USA,02142","Amazon Central Machine Learning, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Cambridge,MA,USA,02142","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Central Machine Learning, Adelaide, SA, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.2995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45831568,"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":"881","last_page":"885"},"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":0.9986000061035156,"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":0.991100013256073,"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":0.8224488496780396},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6772828698158264},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6370433568954468},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5358617901802063},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5192632675170898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4677714705467224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45761600136756897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.347697377204895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224488496780396},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6772828698158264},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6370433568954468},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5358617901802063},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5192632675170898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4677714705467224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45761600136756897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.347697377204895},{"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/icassp48485.2024.10445742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2146241755","https://openalex.org/W2591013610","https://openalex.org/W2605646998","https://openalex.org/W2963794569","https://openalex.org/W2963930099","https://openalex.org/W2979507862","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3133128010","https://openalex.org/W3135818473","https://openalex.org/W3167456680","https://openalex.org/W3178592608","https://openalex.org/W3195051419","https://openalex.org/W3197827948","https://openalex.org/W6637242042"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2562400057"],"abstract_inverted_index":{"Cross-triggering":[0],"is":[1,54,72,159],"a":[2,42,47,144,177],"critical":[3],"problem":[4,28,40],"for":[5,78,122],"applications":[6],"of":[7,88,97,107,125],"audio":[8,133],"event":[9,62,90],"detection":[10,124,184],"(AED),":[11],"particularly":[12],"in":[13,29,81,85,94,167,174,182],"low-resource":[14],"settings.":[15,170],"However,":[16],"not":[17,21,67],"much":[18],"attention":[19],"(if":[20],"none)":[22],"has":[23],"been":[24],"paid":[25],"to":[26,56,74,161,180],"this":[27,35,39],"the":[30,70,75,83,86,95,98,105,108,123,156,164,172,183],"AED":[31,114],"research":[32],"community.":[33],"In":[34],"work,":[36],"we":[37,111],"tackle":[38],"via":[41],"regularization":[43],"approach.":[44],"We":[45],"propose":[46],"regularizer,":[48,52,110],"namely":[49],"mutual":[50],"exclusivity":[51,59],"that":[53,135,155],"able":[55,160],"enforce":[57],"pairwise":[58],"between":[60],"two":[61,131],"classes":[63],"when":[64],"they":[65],"do":[66],"co-occur.":[68],"When":[69],"regularizer":[71],"added":[73],"loss":[76],"function":[77],"network":[79,120],"training,":[80],"effect,":[82],"increase":[84],"score":[87],"one":[89],"class":[91],"will":[92],"result":[93],"decrease":[96],"other":[99],"and":[100,128,140],"vice":[101],"versa.":[102],"To":[103],"quantify":[104],"effectiveness":[106],"proposed":[109,157],"developed":[112],"an":[113],"system":[115],"based":[116],"on":[117,143],"convolutional":[118],"neural":[119],"(CNN)":[121],"hand":[126],"clap":[127],"door":[129],"knock,":[130],"transient":[132],"events":[134],"share":[136],"similar":[137],"spectro-temporal":[138],"profiles,":[139],"conducted":[141],"experiments":[142],"large-scale":[145],"real-world":[146],"dataset":[147],"(around":[148],"274.2":[149],"hours).":[150],"The":[151],"experimental":[152,169],"results":[153],"show":[154],"approach":[158],"largely":[162],"mitigate":[163],"cross-triggering":[165],"issue":[166],"various":[168],"Furthermore,":[171],"reduction":[173],"cross-triggering,":[175],"as":[176],"result,":[178],"leads":[179],"improvement":[181],"performance.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}