{"id":"https://openalex.org/W4387120668","doi":"https://doi.org/10.3390/info14100527","title":"Comparative Analysis of Deep Learning Architectures and Vision Transformers for Musical Key Estimation","display_name":"Comparative Analysis of Deep Learning Architectures and Vision Transformers for Musical Key Estimation","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387120668","doi":"https://doi.org/10.3390/info14100527"},"language":"en","primary_location":{"id":"doi:10.3390/info14100527","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100527","pdf_url":"https://www.mdpi.com/2078-2489/14/10/527/pdf?version=1695883408","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/14/10/527/pdf?version=1695883408","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066207642","display_name":"Manav Garg","orcid":"https://orcid.org/0000-0002-5979-2079"},"institutions":[{"id":"https://openalex.org/I165831266","display_name":"Nirma University","ror":"https://ror.org/05qkq7x38","country_code":"IN","type":"education","lineage":["https://openalex.org/I165831266"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manav Garg","raw_affiliation_strings":["Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, Gujarat, India","institution_ids":["https://openalex.org/I165831266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042323640","display_name":"Pranshav Gajjar","orcid":"https://orcid.org/0000-0002-1730-9640"},"institutions":[{"id":"https://openalex.org/I165831266","display_name":"Nirma University","ror":"https://ror.org/05qkq7x38","country_code":"IN","type":"education","lineage":["https://openalex.org/I165831266"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranshav Gajjar","raw_affiliation_strings":["Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, Gujarat, India","institution_ids":["https://openalex.org/I165831266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000512316","display_name":"Pooja Shah","orcid":"https://orcid.org/0000-0002-9478-7021"},"institutions":[{"id":"https://openalex.org/I33586908","display_name":"Pandit Deendayal Energy University","ror":"https://ror.org/02nsv5p42","country_code":"IN","type":"education","lineage":["https://openalex.org/I33586908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pooja Shah","raw_affiliation_strings":["School of Technology, Pandit Deendayal Energy University, Gandhinagar 382426, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"School of Technology, Pandit Deendayal Energy University, Gandhinagar 382426, Gujarat, India","institution_ids":["https://openalex.org/I33586908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102672713","display_name":"Madhu Shukla","orcid":null},"institutions":[{"id":"https://openalex.org/I3132999081","display_name":"Marwadi University","ror":"https://ror.org/030dn1812","country_code":"IN","type":"education","lineage":["https://openalex.org/I3132999081"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhu Shukla","raw_affiliation_strings":["Department of Computer Engineering\u2014AI and BDA, Marwadi University, Rajkot 360003, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering\u2014AI and BDA, Marwadi University, Rajkot 360003, Gujarat, India","institution_ids":["https://openalex.org/I3132999081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031377837","display_name":"Biswaranjan Acharya","orcid":"https://orcid.org/0000-0002-6506-9207"},"institutions":[{"id":"https://openalex.org/I3132999081","display_name":"Marwadi University","ror":"https://ror.org/030dn1812","country_code":"IN","type":"education","lineage":["https://openalex.org/I3132999081"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Biswaranjan Acharya","raw_affiliation_strings":["Department of Computer Engineering\u2014AI and BDA, Marwadi University, Rajkot 360003, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering\u2014AI and BDA, Marwadi University, Rajkot 360003, Gujarat, India","institution_ids":["https://openalex.org/I3132999081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046194597","display_name":"Vassilis C. Gerogiannis","orcid":"https://orcid.org/0000-0002-9895-7606"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Vassilis C. Gerogiannis","raw_affiliation_strings":["Department of Digital Systems, University of Thessaly, 41500 Larissa, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Digital Systems, University of Thessaly, 41500 Larissa, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004664070","display_name":"Andreas Kanavos","orcid":"https://orcid.org/0000-0002-9964-4134"},"institutions":[{"id":"https://openalex.org/I187792471","display_name":"Ionian University","ror":"https://ror.org/01xm4n520","country_code":"GR","type":"education","lineage":["https://openalex.org/I187792471"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Andreas Kanavos","raw_affiliation_strings":["Department of Informatics, Ionian University, 49100 Corfu, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Ionian University, 49100 Corfu, Greece","institution_ids":["https://openalex.org/I187792471"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004664070","https://openalex.org/A5031377837","https://openalex.org/A5046194597"],"corresponding_institution_ids":["https://openalex.org/I145722265","https://openalex.org/I187792471","https://openalex.org/I3132999081"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":3.3287,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93440495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"14","issue":"10","first_page":"527","last_page":"527"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7261882424354553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7234718799591064},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7232672572135925},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6424388289451599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6075042486190796},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5481099486351013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4769905209541321},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4174238443374634},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16037696599960327},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.10461530089378357},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.093645840883255}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7261882424354553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7234718799591064},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7232672572135925},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6424388289451599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075042486190796},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5481099486351013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4769905209541321},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4174238443374634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16037696599960327},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.10461530089378357},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.093645840883255},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info14100527","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100527","pdf_url":"https://www.mdpi.com/2078-2489/14/10/527/pdf?version=1695883408","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:377fa1d2039e4da0a9f9b242831aec67","is_oa":true,"landing_page_url":"https://doaj.org/article/377fa1d2039e4da0a9f9b242831aec67","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 14, Iss 10, p 527 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/14/10/527/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info14100527","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info14100527","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100527","pdf_url":"https://www.mdpi.com/2078-2489/14/10/527/pdf?version=1695883408","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8313240209","display_name":null,"funder_award_id":"PNURSP2023R138","funder_id":"https://openalex.org/F4320322484","funder_display_name":"Princess Nourah Bint Abdulrahman University"}],"funders":[{"id":"https://openalex.org/F4320322484","display_name":"Princess Nourah Bint Abdulrahman University","ror":"https://ror.org/05b0cyh02"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387120668.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W296482991","https://openalex.org/W1518164296","https://openalex.org/W1597723231","https://openalex.org/W1982446897","https://openalex.org/W2024595034","https://openalex.org/W2042978954","https://openalex.org/W2054623822","https://openalex.org/W2073228908","https://openalex.org/W2079580423","https://openalex.org/W2111007352","https://openalex.org/W2133824856","https://openalex.org/W2165911145","https://openalex.org/W2194775991","https://openalex.org/W2294150958","https://openalex.org/W2311634379","https://openalex.org/W2537159808","https://openalex.org/W2775487773","https://openalex.org/W2896135735","https://openalex.org/W2931364255","https://openalex.org/W2963446712","https://openalex.org/W2990396912","https://openalex.org/W3081288434","https://openalex.org/W3099425575","https://openalex.org/W3105159616","https://openalex.org/W3138516171","https://openalex.org/W3176277033","https://openalex.org/W3200707343","https://openalex.org/W3208006140","https://openalex.org/W3211787299","https://openalex.org/W3217314753","https://openalex.org/W4206706211","https://openalex.org/W4214612132","https://openalex.org/W4214770363","https://openalex.org/W4221116149","https://openalex.org/W4226322728","https://openalex.org/W4290024101","https://openalex.org/W4292622404","https://openalex.org/W4293257826","https://openalex.org/W4295219506","https://openalex.org/W4306175696","https://openalex.org/W4312957757","https://openalex.org/W4313906959","https://openalex.org/W4317505629","https://openalex.org/W4320730097","https://openalex.org/W4360612734","https://openalex.org/W6603977465","https://openalex.org/W6677757839","https://openalex.org/W6698379102","https://openalex.org/W6782073311","https://openalex.org/W6786165050","https://openalex.org/W6797854001","https://openalex.org/W6843035694"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397","https://openalex.org/W3014300295","https://openalex.org/W3164822677","https://openalex.org/W2795261237"],"abstract_inverted_index":{"The":[0,161],"musical":[1,174],"key":[2,33,175],"serves":[3],"as":[4,27],"a":[5,9,57,80,98,138,183,219],"crucial":[6],"element":[7],"in":[8,38,72,141,153,167,208,228],"piece,":[10],"offering":[11],"vital":[12],"insights":[13,203],"into":[14,115],"the":[15,84,116,122,131,158,171,188],"tonal":[16],"center,":[17],"harmonic":[18],"structure,":[19],"and":[20,29,42,51,65,134,145,179,190,196,212,224],"chord":[21],"progressions":[22],"while":[23],"enabling":[24],"tasks":[25],"such":[26],"transposition":[28],"arrangement.":[30],"Moreover,":[31],"accurate":[32,178],"estimation":[34],"finds":[35],"practical":[36,205],"applications":[37],"music":[39,44,209,214],"recommendation":[40,210],"systems":[41,211],"automatic":[43,213],"transcription,":[45],"making":[46],"it":[47],"relevant":[48],"across":[49],"academic":[50],"industrial":[52],"domains.":[53,74],"This":[54],"paper":[55],"presents":[56],"comprehensive":[58],"comparison":[59],"between":[60],"standard":[61],"deep":[62,90,100,127,193],"learning":[63,91,101,128,194],"architectures":[64,195],"emerging":[66],"vision":[67,109,132,197],"transformers,":[68,198],"leveraging":[69],"their":[70,77,168],"success":[71],"various":[73],"We":[75],"evaluate":[76],"performance":[78,143,152],"on":[79,121],"specific":[81],"subset":[82],"of":[83,106,125,163,173,192],"GTZAN":[85],"dataset,":[86],"analyzing":[87],"six":[88],"different":[89],"models.":[92],"Our":[93,216],"results":[94],"demonstrate":[95,150],"that":[96],"DenseNet,":[97],"conventional":[99],"architecture,":[102],"achieves":[103],"remarkable":[104],"accuracy":[105],"91.64%,":[107],"outperforming":[108],"transformers.":[110],"However,":[111],"we":[112,199],"delve":[113],"deeper":[114],"analysis":[117],"to":[118,157,170],"shed":[119],"light":[120],"temporal":[123,154],"characteristics":[124],"each":[126],"model.":[129],"Notably,":[130],"transformer":[133,136],"SWIN":[135],"exhibit":[137],"slight":[139],"decrease":[140],"overall":[142],"(1.82%":[144],"2.29%,":[146],"respectively),":[147],"yet":[148],"they":[149],"superior":[151],"metrics":[155],"compared":[156],"DenseNet":[159],"architecture.":[160],"significance":[162],"our":[164],"findings":[165],"lies":[166],"contribution":[169],"field":[172],"estimation,":[176],"where":[177],"efficient":[180],"algorithms":[181],"play":[182],"pivotal":[184],"role.":[185],"By":[186],"examining":[187],"strengths":[189],"weaknesses":[191],"can":[200],"gain":[201],"valuable":[202],"for":[204,221],"implementations,":[206],"particularly":[207],"transcription.":[215],"research":[217],"provides":[218],"foundation":[220],"future":[222],"advancements":[223],"encourages":[225],"further":[226],"exploration":[227],"this":[229],"area.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
