{"id":"https://openalex.org/W4392909775","doi":"https://doi.org/10.1109/icassp48485.2024.10447697","title":"Max-AST: Combining Convolution, Local and Global Self-Attentions for Audio Event Classification","display_name":"Max-AST: Combining Convolution, Local and Global Self-Attentions for Audio Event Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909775","doi":"https://doi.org/10.1109/icassp48485.2024.10447697"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447697","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/A5108635068","display_name":"Tony Alex","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tony Alex","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037459105","display_name":"Sara Atito Ali Ahmed","orcid":"https://orcid.org/0000-0002-7576-5791"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sara Ahmed","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075260187","display_name":"Armin Mustafa","orcid":"https://orcid.org/0000-0002-1779-2775"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Armin Mustafa","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778579","display_name":"Muhammad Awais","orcid":"https://orcid.org/0000-0002-1122-0709"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Muhammad Awais","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Philip JB Jackson","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108635068"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.6462,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82951775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1061","last_page":"1065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9611999988555908,"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":0.9491999745368958,"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/convolution","display_name":"Convolution (computer science)","score":0.7075304388999939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6591628789901733},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6437808275222778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49078211188316345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40578901767730713},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07222175598144531},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.048176199197769165}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7075304388999939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591628789901733},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6437808275222778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49078211188316345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40578901767730713},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07222175598144531},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.048176199197769165},{"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/icassp48485.2024.10447697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447697","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":34,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2052666245","https://openalex.org/W2331143823","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2768188490","https://openalex.org/W2797583228","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2963163009","https://openalex.org/W2983446232","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3138516171","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W4212774754","https://openalex.org/W4226442948","https://openalex.org/W4285483774","https://openalex.org/W4287236261","https://openalex.org/W4309957268","https://openalex.org/W4372260443","https://openalex.org/W4372267124","https://openalex.org/W6750665317","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6763367864","https://openalex.org/W6784333009","https://openalex.org/W6796698253","https://openalex.org/W6796931752","https://openalex.org/W6810003034","https://openalex.org/W6840200333","https://openalex.org/W6840952533"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"the":[1,16,42,65,83,97,123,134],"domain":[2],"of":[3,44,80,118,136,138],"audio":[4,84,142],"transformer":[5,59,98],"architectures,":[6],"prior":[7,108],"research":[8],"has":[9],"extensively":[10],"investigated":[11],"isotropic":[12],"architectures":[13,24],"that":[14,25],"capture":[15],"global":[17,31,53,93],"context":[18,32],"through":[19],"full":[20,125],"self-attention":[21],"and":[22,52,92,110],"hierarchical":[23,34],"progressively":[26],"transition":[27],"from":[28],"local":[29,51,90],"to":[30,82,107,120,132],"utilising":[33],"structures":[35],"with":[36,49],"convolutions":[37],"or":[38],"window-based":[39],"attention.":[40],"However,":[41],"idea":[43],"imbuing":[45],"each":[46,137],"individual":[47],"block":[48],"both":[50],"contexts,":[54],"thereby":[55],"creating":[56],"a":[57],"hybrid":[58],"block,":[60],"remains":[61],"relatively":[62],"under-explored":[63],"in":[64,95,104],"field.To":[66],"facilitate":[67],"this":[68],"exploration,":[69],"we":[70,128],"introduce":[71],"Multi":[72],"Axis":[73],"Audio":[74],"Spectrogram":[75],"Transformer":[76],"(Max-AST),":[77],"an":[78],"adaptation":[79],"MaxViT":[81],"domain.":[85],"Our":[86],"approach":[87],"leverages":[88],"convolution,":[89],"window-attention,":[91],"grid-attention":[94],"all":[96],"blocks.":[99],"The":[100,145],"proposed":[101],"model":[102],"excels":[103],"efficiency":[105],"compared":[106],"methods":[109],"consistently":[111],"outperforms":[112],"state-of-the-art":[113],"techniques,":[114],"achieving":[115],"significant":[116],"gains":[117],"up":[119],"2.6%":[121],"on":[122,141],"AudioSet":[124],"set.":[126],"Further,":[127],"performed":[129],"detailed":[130],"ablations":[131],"analyse":[133],"impact":[135],"these":[139],"components":[140],"feature":[143],"learning.":[144],"source":[146],"code":[147],"is":[148],"available":[149],"at":[150],"https://github.com/ta012/MaxAST.git":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}