{"id":"https://openalex.org/W4205471450","doi":"https://doi.org/10.23919/eusipco54536.2021.9616348","title":"Attention Augmented CNNs for Musical Instrument Identification","display_name":"Attention Augmented CNNs for Musical Instrument Identification","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205471450","doi":"https://doi.org/10.23919/eusipco54536.2021.9616348"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616348","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616348","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5004042624","display_name":"Andrew Kier Wise","orcid":"https://orcid.org/0000-0003-0501-2986"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Wise","raw_affiliation_strings":["Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075357799","display_name":"Anthony S. Maida","orcid":"https://orcid.org/0000-0003-2586-2865"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony S. Maida","raw_affiliation_strings":["Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981174","display_name":"Ashok Kumar","orcid":"https://orcid.org/0000-0002-9740-1219"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Kumar","raw_affiliation_strings":["Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Computer Studies University of Louisiana at Lafayette,Lafayette,Louisiana,70504","institution_ids":["https://openalex.org/I79516672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004042624"],"corresponding_institution_ids":["https://openalex.org/I79516672"],"apc_list":null,"apc_paid":null,"fwci":1.0322,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82404298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"380"},"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":0.9969000220298767,"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":0.994700014591217,"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/spectrogram","display_name":"Spectrogram","score":0.8899174928665161},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7223962545394897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092754244804382},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6552548408508301},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.596906840801239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5820765495300293},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5516272783279419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5403128266334534},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5303764343261719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4849298298358917},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.48006805777549744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25370481610298157},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.14523202180862427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1263841688632965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07979226112365723}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8899174928665161},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7223962545394897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092754244804382},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6552548408508301},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.596906840801239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5820765495300293},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5516272783279419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403128266334534},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5303764343261719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4849298298358917},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.48006805777549744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25370481610298157},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.14523202180862427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1263841688632965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07979226112365723},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616348","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616348","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":30,"referenced_works":["https://openalex.org/W409429913","https://openalex.org/W1590102137","https://openalex.org/W1979624743","https://openalex.org/W2076608692","https://openalex.org/W2081293863","https://openalex.org/W2109903591","https://openalex.org/W2133564696","https://openalex.org/W2191779130","https://openalex.org/W2196753680","https://openalex.org/W2261407818","https://openalex.org/W2410860376","https://openalex.org/W2433636802","https://openalex.org/W2512831117","https://openalex.org/W2896457183","https://openalex.org/W2919624000","https://openalex.org/W2981413347","https://openalex.org/W2990912900","https://openalex.org/W2991373524","https://openalex.org/W3004440566","https://openalex.org/W3098670224","https://openalex.org/W4385245566","https://openalex.org/W6614244475","https://openalex.org/W6635274319","https://openalex.org/W6645357640","https://openalex.org/W6679434410","https://openalex.org/W6687624220","https://openalex.org/W6692946518","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6760601182"],"related_works":["https://openalex.org/W2900550435","https://openalex.org/W2743258233","https://openalex.org/W4320925816","https://openalex.org/W2758063741","https://openalex.org/W2977314777","https://openalex.org/W2613736958","https://openalex.org/W2909857627","https://openalex.org/W4206100758","https://openalex.org/W3159557112","https://openalex.org/W4205471450"],"abstract_inverted_index":{"We":[0,90],"study":[1],"the":[2,35,76,81,85,88,92,103,114,129,134,158],"effectiveness":[3],"of":[4,87,94,105,121,136,164],"attention":[5,45,95,107,168],"augmented":[6,160],"convolutional":[7,42,52],"neural":[8],"networks":[9,159],"for":[10,167,184],"musical":[11],"instrument":[12],"identification":[13],"in":[14,99,108],"audio,":[15],"which":[16],"is":[17,72,116],"an":[18],"unsolved":[19],"problem.":[20],"Attention":[21,71],"augmentation":[22,96],"has":[23],"not":[24],"previously":[25],"been":[26],"applied":[27],"to":[28,65,74,79,97,101,113,150,171],"this":[29,109],"task.":[30,111],"The":[31,47,59,191],"proposed":[32],"architecture":[33],"augments":[34],"final":[36,60],"convolution":[37,98,192],"modules":[38,53],"from":[39,128],"a":[40,117,122],"baseline":[41],"template":[43],"with":[44,161],"mechanisms.":[46],"network":[48,115],"contains":[49],"five":[50,56],"total":[51],"followed":[54],"by":[55],"dense":[57],"layers.":[58],"layer":[61],"uses":[62],"softmax":[63],"output":[64],"categorize":[66],"19":[67],"different":[68,144],"orchestral":[69],"instruments.":[70],"introduced":[73],"enhance":[75],"network's":[77],"ability":[78],"extract":[80],"casual":[82],"structure":[83],"underlying":[84],"formation":[86],"spectrograms.":[89],"manipulate":[91],"ratio":[93],"order":[100],"assess":[102,151],"efficacy":[104],"adding":[106],"particular":[110],"Input":[112],"2D":[118],"sound":[119],"spectrogram":[120,145],"1s":[123],"duration":[124],"audio":[125],"file":[126],"taken":[127],"London":[130],"Philharmonic":[131],"Orchestra":[132],"and":[133,148,176,180,186,198],"University":[135],"Iowa":[137],"Musical":[138],"Instrument":[139],"datasets.":[140],"Experiments":[141],"use":[142],"two":[143],"types,":[146],"CQT":[147,187],"STFT,":[149],"their":[152,165,173],"relative":[153],"merits.":[154],"Results":[155],"show":[156],"that":[157],"25":[162],"%":[163,179,197,200],"filters":[166],"are":[169],"able":[170],"outperform":[172],"only-convolutional":[174],"counterparts":[175],"achieve":[177,195],"95.09":[178],"92.40%":[181],"overall":[182],"accuracy":[183],"STFT":[185],"input":[188],"spectrograms,":[189],"respectively.":[190,202],"only":[193],"models":[194],"84.94":[196],"91.43":[199],"accuracy,":[201]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}