{"id":"https://openalex.org/W4372260403","doi":"https://doi.org/10.1109/icassp49357.2023.10096110","title":"Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation","display_name":"Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260403","doi":"https://doi.org/10.1109/icassp49357.2023.10096110"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5103009549","display_name":"Florian Schmid","orcid":"https://orcid.org/0009-0007-4988-6067"},"institutions":[{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]},{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT","US"],"is_corresponding":true,"raw_author_name":"Florian Schmid","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU)","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU)","institution_ids":["https://openalex.org/I4210142635"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220503","display_name":"Khaled Koutini","orcid":"https://orcid.org/0000-0002-9193-732X"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Khaled Koutini","raw_affiliation_strings":["Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]},{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU)","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU)","institution_ids":["https://openalex.org/I4210142635"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103009549"],"corresponding_institution_ids":["https://openalex.org/I121883995","https://openalex.org/I4210142635"],"apc_list":null,"apc_paid":null,"fwci":9.3736,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98754304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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":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":0.9991999864578247,"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":0.9988999962806702,"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":0.7549169063568115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6734591126441956},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6527590751647949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5371978878974915},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5228136777877808},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4693114757537842},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41757437586784363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3799830675125122},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3540499806404114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1765901744365692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08774960041046143},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08705651760101318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549169063568115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6734591126441956},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6527590751647949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371978878974915},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5228136777877808},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4693114757537842},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41757437586784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799830675125122},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3540499806404114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1765901744365692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08774960041046143},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08705651760101318},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2108598243","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2765407302","https://openalex.org/W2936774411","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3145444543","https://openalex.org/W3165587897","https://openalex.org/W3170224286","https://openalex.org/W3170874841","https://openalex.org/W3172353912","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W4226165006","https://openalex.org/W4226442948","https://openalex.org/W4285483774","https://openalex.org/W4297775537","https://openalex.org/W4312443924","https://openalex.org/W4375839990","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6762718338","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6793164127","https://openalex.org/W6796651704","https://openalex.org/W6809596386","https://openalex.org/W6840200333"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Audio":[0,8],"Spectrogram":[1],"Transformer":[2],"models":[3,82,98,106],"rule":[4],"the":[5,22,73],"field":[6],"of":[7,40,88,99,113],"Tagging,":[9],"outrunning":[10],"previously":[11],"dominating":[12],"Convolutional":[13],"Neural":[14],"Networks":[15],"(CNNs).":[16],"Their":[17],"superiority":[18],"is":[19],"based":[20,57,77],"on":[21,58,78,116],"ability":[23],"to":[24,47,108],"scale":[25],"up":[26,107],"and":[27,43,72,90,93],"exploit":[28],"large-scale":[29],"datasets":[30],"such":[31],"as":[32],"AudioSet.":[33,117],"However,":[34],"Transformers":[35],"are":[36],"demanding":[37],"in":[38,81,86],"terms":[39,87],"model":[41],"size":[42],"computational":[44,91],"requirements":[45],"compared":[46],"CNNs.":[48],"We":[49,96],"propose":[50],"a":[51,109],"training":[52,70],"procedure":[53],"for":[54],"efficient":[55,74],"CNNs":[56],"offline":[59],"Knowledge":[60],"Distillation":[61],"(KD)":[62],"from":[63,104],"high-performing":[64],"yet":[65],"complex":[66],"transformers.":[67],"The":[68],"proposed":[69],"schema":[71],"CNN":[75],"design":[76],"MobileNetV3":[79],"results":[80],"outperforming":[83],"previous":[84],"solutions":[85],"parameter":[89],"efficiency":[92],"prediction":[94],"performance.":[95],"provide":[97],"different":[100],"complexity":[101],"levels,":[102],"scaling":[103],"low-complexity":[105],"new":[110],"state-of-the-art":[111],"performance":[112],".483":[114],"mAP":[115],"<sup":[118],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[120]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}