{"id":"https://openalex.org/W4414872983","doi":"https://doi.org/10.3390/info16100864","title":"Explainable Instrument Classification: From MFCC Mean-Vector Models to CNNs on MFCC and Mel-Spectrograms with t-SNE and Grad-CAM Insights","display_name":"Explainable Instrument Classification: From MFCC Mean-Vector Models to CNNs on MFCC and Mel-Spectrograms with t-SNE and Grad-CAM Insights","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W4414872983","doi":"https://doi.org/10.3390/info16100864"},"language":"en","primary_location":{"id":"doi:10.3390/info16100864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100864","pdf_url":"https://www.mdpi.com/2078-2489/16/10/864/pdf?version=1759655462","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/2078-2489/16/10/864/pdf?version=1759655462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119868424","display_name":"Tommaso Senatori","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Senatori","raw_affiliation_strings":["Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy"],"raw_orcid":"https://orcid.org/0009-0009-5521-7315","affiliations":[{"raw_affiliation_string":"Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119868425","display_name":"Daniela Nardone","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniela Nardone","raw_affiliation_strings":["Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy"],"raw_orcid":"https://orcid.org/0009-0001-1279-4966","affiliations":[{"raw_affiliation_string":"Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002323128","display_name":"Michele Lo Giudice","orcid":"https://orcid.org/0000-0002-2660-0405"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Lo Giudice","raw_affiliation_strings":["Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2660-0405","affiliations":[{"raw_affiliation_string":"Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036976911","display_name":"Alessandro Salvini","orcid":"https://orcid.org/0000-0002-5825-1019"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Salvini","raw_affiliation_strings":["Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5825-1019","affiliations":[{"raw_affiliation_string":"Department of Civil, Computer Science and Aeronautical Technologies Engineering, Universit\u00e0 degli Studi Roma Tre, Via V. Volterra 62, 00146 Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002323128"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":5.0578,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95217337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"16","issue":"10","first_page":"864","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7358999848365784,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7358999848365784,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.6535000205039978,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8048999905586243},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6079000234603882},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5891000032424927},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5752999782562256},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4569000005722046}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8048999905586243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671500027179718},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2720000147819519},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info16100864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100864","pdf_url":"https://www.mdpi.com/2078-2489/16/10/864/pdf?version=1759655462","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:98d50f4c265e416a995bb00e81b909d4","is_oa":true,"landing_page_url":"https://doaj.org/article/98d50f4c265e416a995bb00e81b909d4","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,"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":"Information, Vol 16, Iss 10, p 864 (2025)","raw_type":"article"},{"id":"pmh:oai:iris.uniroma3.it:11590/524219","is_oa":true,"landing_page_url":"https://hdl.handle.net/11590/524219","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3390/info16100864","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16100864","pdf_url":"https://www.mdpi.com/2078-2489/16/10/864/pdf?version=1759655462","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414872983.pdf","grobid_xml":"https://content.openalex.org/works/W4414872983.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1988068457","https://openalex.org/W2029049232","https://openalex.org/W2031300154","https://openalex.org/W2166693890","https://openalex.org/W2191779130","https://openalex.org/W2410860376","https://openalex.org/W2556437173","https://openalex.org/W3132799936","https://openalex.org/W4206995848","https://openalex.org/W4224277409","https://openalex.org/W4280618035","https://openalex.org/W4313178214","https://openalex.org/W4320157594","https://openalex.org/W4386918931","https://openalex.org/W4389619460","https://openalex.org/W4389917623","https://openalex.org/W4399291297","https://openalex.org/W4401664983","https://openalex.org/W4405558603","https://openalex.org/W4408678626","https://openalex.org/W4410252944","https://openalex.org/W4411471303"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"automatic":[4],"system":[5],"for":[6,120,131,215],"the":[7,40,48,103,106,114,126,142,153,158,163,167,192,210,216],"classification":[8,29,183],"of":[9,42,67,105,124,157,182],"musical":[10],"instruments":[11],"from":[12,47],"audio":[13,49],"recordings.":[14],"The":[15,36,62,77,178],"project":[16],"leverages":[17],"deep":[18],"learning":[19,83],"(DL)":[20],"techniques":[21,110],"to":[22,72,113,145],"achieve":[23],"its":[24],"objective,":[25],"exploring":[26],"three":[27],"different":[28],"approaches":[30],"based":[31],"on":[32,95,141,224],"distinct":[33],"input":[34,71],"representations.":[35],"first":[37],"method":[38],"involves":[39],"extraction":[41],"Mel-Frequency":[43],"Cepstral":[44],"Coefficients":[45],"(MFCCs)":[46],"files,":[50],"which":[51,169],"are":[52,150],"then":[53],"fed":[54],"into":[55,102],"a":[56,73,121],"two-dimensional":[57],"convolutional":[58,193],"neural":[59],"network":[60,127],"(Conv2D).":[61],"second":[63],"approach":[64,79],"makes":[65],"use":[66],"mel-spectrogram":[68],"images":[69],"as":[70],"similar":[74],"Conv2D":[75,115],"architecture.":[76],"third":[78],"employs":[80],"conventional":[81],"machine":[82],"(ML)":[84],"classifiers,":[85],"including":[86],"Logistic":[87,202],"Regression,":[88],"K-Nearest":[89],"Neighbors,":[90],"and":[91,195,201,219],"Random":[92,196],"Forest,":[93],"trained":[94],"MFCC-derived":[96],"feature":[97,154],"vectors.":[98],"To":[99],"gain":[100],"insight":[101],"behavior":[104],"DL":[107],"model,":[108],"explainability":[109],"were":[111,185],"applied":[112],"model":[116],"using":[117],"mel-spectrograms,":[118],"allowing":[119],"better":[122],"understanding":[123],"how":[125,147],"interprets":[128],"relevant":[129],"features":[130],"classification.":[132],"Additionally,":[133],"t-distributed":[134],"stochastic":[135],"neighbor":[136],"embedding":[137],"(t-SNE)":[138],"was":[139,162,170],"employed":[140],"MFCC":[143],"vectors":[144],"visualize":[146],"instrument":[148],"classes":[149],"organized":[151],"in":[152,180],"space.":[155],"One":[156],"main":[159],"challenges":[160],"encountered":[161],"class":[164,227],"imbalance":[165],"within":[166],"dataset,":[168,218],"addressed":[171],"by":[172],"assigning":[173],"class-specific":[174],"weights":[175],"during":[176],"training.":[177],"results,":[179],"terms":[181],"accuracy,":[184],"very":[186],"satisfactory":[187],"across":[188],"all":[189],"approaches,":[190],"with":[191],"models":[194],"Forest":[197],"achieving":[198],"around":[199],"97\u201398%,":[200],"Regression":[203],"yielding":[204],"slightly":[205],"lower":[206],"performance.":[207],"In":[208],"conclusion,":[209],"proposed":[211],"methods":[212],"proved":[213],"effective":[214],"selected":[217],"future":[220],"work":[221],"may":[222],"focus":[223],"further":[225],"improving":[226],"balance":[228],"techniques.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}