{"id":"https://openalex.org/W4392904001","doi":"https://doi.org/10.1109/icassp48485.2024.10446348","title":"CED: Consistent Ensemble Distillation for Audio Tagging","display_name":"CED: Consistent Ensemble Distillation for Audio Tagging","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904001","doi":"https://doi.org/10.1109/icassp48485.2024.10446348"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446348","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/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113948981","display_name":"Zhiyong Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":6.3503,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.97322911,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"291","last_page":"295"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.7857626080513},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7128480672836304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.66246497631073},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5742672085762024},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5722116231918335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5321584939956665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4488700032234192},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4484444260597229},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42745858430862427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33996134996414185},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1783280074596405},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11359530687332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857626080513},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7128480672836304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.66246497631073},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5742672085762024},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5722116231918335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5321584939956665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4488700032234192},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4484444260597229},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42745858430862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33996134996414185},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1783280074596405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11359530687332153},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446348","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2747329762","https://openalex.org/W2936774411","https://openalex.org/W3094550259","https://openalex.org/W3170224286","https://openalex.org/W3196974791","https://openalex.org/W4212774754","https://openalex.org/W4224917059","https://openalex.org/W4226442948","https://openalex.org/W4295312788","https://openalex.org/W4296068594","https://openalex.org/W4307823382","https://openalex.org/W4308868387","https://openalex.org/W4311731188","https://openalex.org/W4312048190","https://openalex.org/W4312671791","https://openalex.org/W4372260403","https://openalex.org/W4372260579","https://openalex.org/W4375869243","https://openalex.org/W4375869340","https://openalex.org/W4379251221","https://openalex.org/W4402112408","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6802298259","https://openalex.org/W6809947431","https://openalex.org/W6840200333","https://openalex.org/W6847495150"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1568097102","https://openalex.org/W2378211422","https://openalex.org/W4390419160","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W2102464536","https://openalex.org/W4225671779","https://openalex.org/W2361332776"],"abstract_inverted_index":{"Augmentation":[0],"and":[1,17,137],"knowledge":[2],"distillation":[3],"(KD)":[4],"are":[5,31,98,139],"well-established":[6],"techniques":[7,30],"employed":[8],"in":[9],"audio":[10],"classification":[11],"tasks,":[12],"aimed":[13],"at":[14],"enhancing":[15],"performance":[16],"reducing":[18],"model":[19,106,125],"sizes":[20],"on":[21,76,133],"the":[22,73,95,101],"widely":[23],"recognized":[24],"Audioset":[25],"(AS)":[26],"benchmark.":[27],"Although":[28],"both":[29],"effective":[32],"individually,":[33],"their":[34],"combined":[35],"use,":[36],"called":[37],"consistent":[38,61],"teaching,":[39],"hasn\u2019t":[40],"been":[41],"explored":[42],"before.":[43],"This":[44],"paper":[45],"proposes":[46],"CED,":[47],"a":[48,104,122,127],"simple":[49],"training":[50],"framework":[51],"that":[52,93],"distils":[53],"student":[54,105],"models":[55,136],"from":[56],"large":[57],"teacher":[58],"ensembles":[59],"with":[60],"teaching.":[62],"To":[63],"achieve":[64],"this,":[65],"CED":[66],"efficiently":[67],"stores":[68],"logits":[69,97],"as":[70,72],"well":[71],"augmentation":[74],"methods":[75],"disk,":[77],"making":[78],"it":[79],"scalable":[80],"to":[81,85],"large-scale":[82],"datasets.":[83],"Central":[84],"CED\u2019s":[86],"efficacy":[87],"is":[88],"its":[89],"label-free":[90],"nature,":[91],"meaning":[92],"only":[94,107],"stored":[96],"used":[99],"for":[100,113],"optimization":[102],"of":[103],"requiring":[108],"0.3%":[109],"additional":[110],"disk":[111],"space":[112],"AS.":[114,134],"The":[115],"study":[116],"trains":[117],"various":[118],"transformer-based":[119],"models,":[120],"including":[121],"10M":[123],"parameter":[124],"achieving":[126],"49.0":[128],"mean":[129],"average":[130],"precision":[131],"(mAP)":[132],"Pretrained":[135],"code":[138],"available":[140],"online.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}