{"id":"https://openalex.org/W4408941383","doi":"https://doi.org/10.1109/access.2025.3555741","title":"Challenges and Perspectives in Interpretable Music Auto-Tagging Using Perceptual Features","display_name":"Challenges and Perspectives in Interpretable Music Auto-Tagging Using Perceptual Features","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408941383","doi":"https://doi.org/10.1109/access.2025.3555741"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3555741","doi":"https://doi.org/10.1109/access.2025.3555741","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555741","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3555741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033631284","display_name":"Vassilis Lyberatos","orcid":"https://orcid.org/0000-0001-8957-0277","observed_orcids":["https://orcid.org/0000-0001-8957-0277"]},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Lyberatos","raw_affiliation_strings":["AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0001-8957-0277","affiliations":[{"raw_affiliation_string":"AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079920369","display_name":"Spyridon Kantarelis","orcid":"https://orcid.org/0000-0001-8034-8047","observed_orcids":["https://orcid.org/0000-0001-8034-8047"]},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Spyridon Kantarelis","raw_affiliation_strings":["AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042494229","display_name":"Edmund Dervakos","orcid":"https://orcid.org/0000-0001-7838-3919","observed_orcids":["https://orcid.org/0000-0001-7838-3919"]},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Edmund Dervakos","raw_affiliation_strings":["AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085359792","display_name":"Giorgos B. Stamou","orcid":"https://orcid.org/0000-0003-1210-9874","observed_orcids":["https://orcid.org/0000-0003-1210-9874"]},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Giorgos Stamou","raw_affiliation_strings":["AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI and Learning Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, AI and Learning Systems Laboratory, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":1.9496,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84197428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"60720","last_page":"60732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002199999988079071,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":9.999999747378752e-05,"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/music-auto-tagging","display_name":"music auto-tagging","score":0.9539999961853027},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.7789999842643738},{"id":"https://openalex.org/keywords/explainable-machine-learning","display_name":"explainable machine learning","score":0.972000002861023},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"audio signal processing","score":0.6729999780654907},{"id":"https://openalex.org/keywords/user-trust","display_name":"user trust","score":0.6819999814033508},{"id":"https://openalex.org/keywords/music-recommendation","display_name":"music recommendation","score":0.6359999775886536},{"id":"https://openalex.org/keywords/music-streaming","display_name":"music streaming","score":0.3840000033378601},{"id":"https://openalex.org/keywords/gtzan","display_name":"GTZAN","score":0.6729999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059418559074402},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6525536775588989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5143588781356812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4639309048652649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3783974051475525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3429874777793884},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16098204255104065},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3555741","doi":"https://doi.org/10.1109/access.2025.3555741","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555741","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ce4c60a4efb94e3f9cb6c697de3def6f","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/ce4c60a4efb94e3f9cb6c697de3def6f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 60720-60732 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3555741","doi":"https://doi.org/10.1109/access.2025.3555741","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555741","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318628","display_name":"Hellenic Academic Libraries Link","ror":"https://ror.org/01wbw2607"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1489285575","https://openalex.org/W2020463305","https://openalex.org/W2026805626","https://openalex.org/W2077073102","https://openalex.org/W2083116372","https://openalex.org/W2095690993","https://openalex.org/W2100171245","https://openalex.org/W2101240583","https://openalex.org/W2123459668","https://openalex.org/W2133824856","https://openalex.org/W2137637927","https://openalex.org/W2154157725","https://openalex.org/W2155413697","https://openalex.org/W2295598076","https://openalex.org/W2439568532","https://openalex.org/W2526050071","https://openalex.org/W2890376498","https://openalex.org/W2891503716","https://openalex.org/W2900374961","https://openalex.org/W2937484199","https://openalex.org/W2943207870","https://openalex.org/W2945976633","https://openalex.org/W2962772482","https://openalex.org/W2997560917","https://openalex.org/W3042845970","https://openalex.org/W3090634605","https://openalex.org/W3135534264","https://openalex.org/W3144236954","https://openalex.org/W3196974791","https://openalex.org/W3201135806","https://openalex.org/W4206908116","https://openalex.org/W4224918495","https://openalex.org/W4235855427","https://openalex.org/W4295073825","https://openalex.org/W4324155120","https://openalex.org/W4388491740","https://openalex.org/W4392904213","https://openalex.org/W4392909519","https://openalex.org/W4393995342","https://openalex.org/W4400762160","https://openalex.org/W4402390208","https://openalex.org/W4402402508","https://openalex.org/W4408353039","https://openalex.org/W6603607804","https://openalex.org/W6637408129","https://openalex.org/W6638787421","https://openalex.org/W6683737379","https://openalex.org/W6704344484","https://openalex.org/W6734862562","https://openalex.org/W6735632633","https://openalex.org/W6737947904","https://openalex.org/W6751512325","https://openalex.org/W6752325027","https://openalex.org/W6756943755","https://openalex.org/W6758949196","https://openalex.org/W6763945542","https://openalex.org/W6764072591","https://openalex.org/W6764574124","https://openalex.org/W6765362075","https://openalex.org/W6768465061","https://openalex.org/W6771230977","https://openalex.org/W6798597329","https://openalex.org/W6843129683","https://openalex.org/W6844040096","https://openalex.org/W6846931942","https://openalex.org/W6853616447","https://openalex.org/W6854553432","https://openalex.org/W6872743839"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W4387697615","https://openalex.org/W2568121504","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,92],"the":[1,10,30,70,97,153,156,160,178,200,211,219],"era":[2],"of":[3,19,42,72,99,111,131],"music":[4,12,102],"streaming":[5],"platforms":[6],"and":[7,21,123,159,171,192,222],"recommendation":[8],"systems,":[9],"automatic":[11],"auto-tagging":[13],"task":[14,31],"has":[15,22,74,84],"gained":[16],"a":[17,66,87,106,182,194],"lot":[18],"traction":[20],"motivated":[23],"researchers":[24],"to":[25,61,127,138,145,185],"develop":[26],"methods":[27],"for":[28,89,101],"solving":[29],"focusing":[32],"on":[33,37,46,65,150],"improving":[34],"performance":[35],"metrics":[36],"baseline":[38,166],"datasets.":[39],"The":[40],"majority":[41],"recent":[43],"approaches":[44],"rely":[45],"deep":[47,120],"neural":[48,121],"networks,":[49,122],"which":[50,134],"despite":[51],"their":[52,63],"impressive":[53],"performance,":[54,205],"are":[55,207],"opaque,":[56],"meaning":[57],"it":[58,83],"is":[59,175,216],"difficult":[60],"explain":[62],"output":[64],"given":[67],"input.":[68],"While":[69],"problem":[71],"interpretability":[73,100],"been":[75,86],"highlighted":[76],"in":[77,168,172,189,193,214],"other":[78],"domains,":[79],"such":[80],"as":[81],"medicine,":[82],"not":[85],"priority":[88],"music-related":[90],"tasks.":[91],"this":[93],"work,":[94],"we":[95],"explored":[96],"usefulness":[98],"auto-tagging.":[103],"We":[104,148,180],"developed":[105],"pipeline":[107],"incorporating":[108],"three":[109,151],"types":[110],"information":[112],"extraction":[113],"procedures:":[114],"1)":[115],"symbolic":[116],"knowledge,":[117],"2)":[118],"auxiliary":[119],"3)":[124],"signal":[125],"processing,":[126],"extract":[128],"perceptual":[129],"features":[130],"audio":[132],"files,":[133],"were":[135],"then":[136],"used":[137],"train":[139],"an":[140],"explainable":[141],"machine":[142],"learning":[143],"model":[144,202],"predict":[146],"tags.":[147],"experimented":[149],"datasets":[152],"MTG-Jamendo":[154],"dataset,":[155,158],"GTZAN":[157],"MagnaTagATune":[161],"dataset.":[162],"Our":[163],"method":[164],"outperforms":[165],"models":[167],"all":[169],"tasks":[170],"some":[173],"cases":[174,209],"competitive":[176],"with":[177],"state-of-the-art.":[179],"conducted":[181],"human":[183],"survey":[184],"evaluate":[186],"user":[187],"trust":[188,221],"our":[190],"methodology":[191],"state-of-the-art":[195,201],"model,":[196],"concluding":[197],"that":[198],"while":[199],"offers":[203],"better":[204],"there":[206],"use":[208],"where":[210],"slight":[212],"deterioration":[213],"accuracy":[215],"outweighed":[217],"by":[218,225],"increased":[220],"value":[223],"provided":[224],"interpretability.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}