{"id":"https://openalex.org/W4372342316","doi":"https://doi.org/10.1109/icassp49357.2023.10096755","title":"Attention Mixup: An Accurate Mixup Scheme Based On Interpretable Attention Mechanism for Multi-Label Audio Classification","display_name":"Attention Mixup: An Accurate Mixup Scheme Based On Interpretable Attention Mechanism for Multi-Label Audio Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342316","doi":"https://doi.org/10.1109/icassp49357.2023.10096755"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096755","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":"conference-paper","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/A5049058927","display_name":"Wuyang Liu","orcid":"https://orcid.org/0000-0003-2790-3069"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuyang Liu","raw_affiliation_strings":["Wuhan University,School of Cyber Science and Engineering","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499462","display_name":"Yanzhen Ren","orcid":"https://orcid.org/0000-0003-0799-5082"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhen Ren","raw_affiliation_strings":["Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education","institution_ids":[]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100723965","display_name":"Jingru Wang","orcid":"https://orcid.org/0000-0001-6196-7213"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingru Wang","raw_affiliation_strings":["Wuhan University,School of Cyber Science and Engineering","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9984999895095825,"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":0.9842000007629395,"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/spectrogram","display_name":"Spectrogram","score":0.8104662895202637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598062753677368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269073843955994},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5181592702865601},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4917180836200714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4844651222229004},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42396241426467896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4231525659561157},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4108811616897583},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2980789542198181},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18505439162254333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11554738879203796},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.08503779768943787}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8104662895202637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598062753677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269073843955994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5181592702865601},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4917180836200714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4844651222229004},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42396241426467896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4231525659561157},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4108811616897583},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2980789542198181},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18505439162254333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11554738879203796},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.08503779768943787},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096755","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3160333138","https://openalex.org/W3162999565","https://openalex.org/W3174402370","https://openalex.org/W3174906557","https://openalex.org/W3196974791","https://openalex.org/W3203468141","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W4226442948","https://openalex.org/W4283809036","https://openalex.org/W4285483774","https://openalex.org/W4307823382","https://openalex.org/W6757817989","https://openalex.org/W6796580215","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2793814466"],"abstract_inverted_index":{"Mixup":[0],"proves":[1],"to":[2,83,104,144],"be":[3],"an":[4,147],"efficient":[5],"data":[6],"augmentation":[7],"method":[8],"on":[9,88,116,140,155],"audio":[10,78],"classification":[11,79,95,119],"tasks.":[12],"Original":[13],"mixup":[14,102],"scheme":[15],"directly":[16],"mixes":[17],"the":[18,28,32,40,68,73,86,89,99,133,138,153],"waveform":[19],"of":[20,31,76,149],"two":[21],"random":[22],"samples,":[23],"which":[24,53],"not":[25],"only":[26,54],"ignores":[27],"temporal":[29],"distribution":[30],"sound":[33,42,60],"events":[34,43,61,142],"but":[35],"may":[36],"also":[37],"interfere":[38],"with":[39,121],"original":[41],"in":[44],"another":[45],"sample.":[46,70],"This":[47],"paper":[48],"proposes":[49],"Attention":[50],"MixUp":[51],"(AMU),":[52],"selects":[55,98],"those":[56],"segments":[57],"that":[58,91,130],"contain":[59],"for":[62,94,101],"mixup,":[63],"rather":[64],"than":[65],"simply":[66],"mixing":[67],"entire":[69],"AMU":[71,131],"utilizes":[72],"attention":[74],"maps":[75],"pretrained":[77],"Vision":[80],"Transformer":[81],"(ViT)":[82],"filter":[84],"out":[85],"patches":[87],"spectrogram":[90],"are":[92],"useful":[93],"and":[96],"then":[97],"regions":[100],"according":[103],"three":[105],"different":[106],"strategies.":[107],"Experimental":[108],"results":[109],"show":[110,129],"a":[111],"remarkable":[112],"improvement":[113],"(+1.9":[114],"mAP)":[115],"state-of-the-art":[117],"Audioset":[118],"methods":[120],"either":[122],"CNN":[123],"or":[124],"ViT":[125],"backbone.":[126],"Further":[127],"experiments":[128],"achieves":[132],"performance":[134],"gain":[135],"by":[136,146],"improving":[137],"accuracy":[139,154],"short":[141],"(0.1s":[143],"2s)":[145],"average":[148],"6.8%":[150],"while":[151],"keeping":[152],"longer":[156],"events.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}