{"id":"https://openalex.org/W4401610131","doi":"https://doi.org/10.1109/icasspw62465.2024.10625974","title":"Dual Knowledge Distillation for Efficient Sound Event Detection","display_name":"Dual Knowledge Distillation for Efficient Sound Event Detection","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401610131","doi":"https://doi.org/10.1109/icasspw62465.2024.10625974"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10625974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100704055","display_name":"Yang Xiao","orcid":"https://orcid.org/0009-0006-2197-122X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang Xiao","raw_affiliation_strings":["Fortemedia Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Fortemedia Singapore,Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Fortemedia Singapore,Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100704055"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5004,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9543313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"690","last_page":"694"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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":0.9908000230789185,"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":0.707374095916748},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6212471723556519},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6126987338066101},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5741981863975525},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5213735699653625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3406248390674591},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15994617342948914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707374095916748},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6212471723556519},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6126987338066101},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5741981863975525},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5213735699653625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3406248390674591},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15994617342948914},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10625974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2296193698","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2912056372","https://openalex.org/W2959539607","https://openalex.org/W2972824267","https://openalex.org/W3015190346","https://openalex.org/W3160333138","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4221149441","https://openalex.org/W4282044900","https://openalex.org/W4311694119","https://openalex.org/W4319586842","https://openalex.org/W4372260505","https://openalex.org/W4385694566","https://openalex.org/W4385822570","https://openalex.org/W6638523607","https://openalex.org/W6638667902","https://openalex.org/W6733814495","https://openalex.org/W6802291199","https://openalex.org/W6846479224","https://openalex.org/W6848208918","https://openalex.org/W6854336076"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W3026162553","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2],"(SED)":[3],"is":[4],"essential":[5],"for":[6,21,44,160,168],"recognizing":[7],"specific":[8],"sounds":[9],"and":[10,149],"their":[11],"temporal":[12,71],"locations":[13],"within":[14,110],"acoustic":[15],"signals.":[16],"This":[17,78,151],"becomes":[18],"challenging":[19],"particularly":[20],"on-device":[22],"applications,":[23],"where":[24],"computational":[25],"resources":[26],"are":[27],"limited.":[28],"To":[29],"address":[30],"this":[31,50],"issue,":[32],"we":[33,97],"introduce":[34,98],"a":[35,64,87,92],"novel":[36],"framework":[37],"referred":[38],"to":[39,83,114],"as":[40],"dual":[41,54,131,157],"knowledge":[42,55,60,94,132,158],"distillation":[43,56,61,101,108,133,159],"developing":[45],"efficient":[46],"SED":[47,128,162],"systems":[48],"in":[49,145],"work.":[51],"Our":[52],"proposed":[53,127,156],"commences":[57],"with":[58,130],"temporal-averaging":[59],"(TAKD),":[62],"utilizing":[63],"mean":[65],"student":[66,75,81,112],"model":[67,82,113],"derived":[68],"from":[69,86],"the":[70,74,80,111,138,153],"averaging":[72],"of":[73,137,147,155],"model\u2019s":[76,140],"parameters.":[77],"allows":[79],"indirectly":[84],"learn":[85],"pre-trained":[88],"teacher":[89],"model,":[90],"ensuring":[91],"stable":[93],"distillation.":[95],"Subsequently,":[96],"embedding-enhanced":[99],"feature":[100],"(EEFD),":[102],"which":[103,164],"involves":[104],"incorporating":[105],"an":[106],"embedding":[107],"layer":[109],"bolster":[115],"contextual":[116],"learning.":[117],"On":[118],"DCASE":[119],"2023":[120],"Task":[121],"4A":[122],"public":[123],"evaluation":[124],"dataset,":[125],"our":[126],"system":[129],"having":[134],"merely":[135],"one-third":[136],"baseline":[139],"parameters,":[141],"demonstrates":[142],"superior":[143],"performance":[144],"terms":[146],"PSDS1":[148],"PSDS2.":[150],"highlights":[152],"importance":[154],"compact":[161],"systems,":[163],"can":[165],"be":[166],"ideal":[167],"edge":[169],"devices.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}