{"id":"https://openalex.org/W4405558603","doi":"https://doi.org/10.3389/frai.2024.1499913","title":"Interpreting CNN models for musical instrument recognition using multi-spectrogram heatmap analysis: a preliminary study","display_name":"Interpreting CNN models for musical instrument recognition using multi-spectrogram heatmap analysis: a preliminary study","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405558603","doi":"https://doi.org/10.3389/frai.2024.1499913","pmid":"https://pubmed.ncbi.nlm.nih.gov/39744740"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1499913","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1499913","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1499913/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1499913/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077571154","display_name":"Rujia Chen","orcid":"https://orcid.org/0000-0001-6744-3509"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Rujia Chen","raw_affiliation_strings":["Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069265006","display_name":"Akbar Ghobakhlou","orcid":"https://orcid.org/0000-0002-8385-2641"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Akbar Ghobakhlou","raw_affiliation_strings":["Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053383719","display_name":"Ajit Narayanan","orcid":"https://orcid.org/0000-0003-3075-7672"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ajit Narayanan","raw_affiliation_strings":["Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering Department, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077571154"],"corresponding_institution_ids":["https://openalex.org/I39854758"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":1.0606,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76903397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"1499913","last_page":"1499913"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9523000121116638,"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":0.9523000121116638,"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/T13996","display_name":"Diverse Musicological Studies","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.002099999925121665,"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":0.8902792930603027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5526161193847656},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5227779746055603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4862898290157318},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4194837510585785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3568946123123169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33414116501808167},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25540897250175476},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1428215205669403},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08339330554008484},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08338332176208496}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8902792930603027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5526161193847656},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5227779746055603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4862898290157318},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4194837510585785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3568946123123169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33414116501808167},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25540897250175476},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1428215205669403},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08339330554008484},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08338332176208496}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/frai.2024.1499913","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1499913","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1499913/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:39744740","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39744740","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:openrepository.aut.ac.nz:10292/18557","is_oa":true,"landing_page_url":"http://hdl.handle.net/10292/18557","pdf_url":"https://openrepository.aut.ac.nz/bitstreams/fc34f54b-b061-43af-92f3-83dd86a23948/download","source":{"id":"https://openalex.org/S4306401809","display_name":"Tuwhera (Auckland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39854758","host_organization_name":"Auckland University of Technology","host_organization_lineage":["https://openalex.org/I39854758"],"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":null,"raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11688478","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11688478","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11688478/pdf/frai-07-1499913.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:a7c2977b3a9b48e5ba8626ea3ea7ba4b","is_oa":false,"landing_page_url":"https://doaj.org/article/a7c2977b3a9b48e5ba8626ea3ea7ba4b","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1499913","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1499913","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1499913/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405558603.pdf","grobid_xml":"https://content.openalex.org/works/W4405558603.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W806587654","https://openalex.org/W1523493493","https://openalex.org/W1849277567","https://openalex.org/W1965419851","https://openalex.org/W1965555277","https://openalex.org/W2107789863","https://openalex.org/W2112796928","https://openalex.org/W2125324924","https://openalex.org/W2143668817","https://openalex.org/W2146950091","https://openalex.org/W2147800946","https://openalex.org/W2164877274","https://openalex.org/W2606176153","https://openalex.org/W2618530766","https://openalex.org/W2765793020","https://openalex.org/W2904634817","https://openalex.org/W2919115771","https://openalex.org/W2931364255","https://openalex.org/W2940841377","https://openalex.org/W2962835968","https://openalex.org/W2964612343","https://openalex.org/W3004440566","https://openalex.org/W3036142472","https://openalex.org/W3145073341","https://openalex.org/W4239789073","https://openalex.org/W4286906101","https://openalex.org/W4287372095","https://openalex.org/W4392908114","https://openalex.org/W6676071220"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2415999852","https://openalex.org/W2030575009","https://openalex.org/W4229975561","https://openalex.org/W2147114809","https://openalex.org/W4390012055","https://openalex.org/W2991141425","https://openalex.org/W2591743215"],"abstract_inverted_index":{"Introduction:":[0],"Musical":[1],"instrument":[2,151],"recognition":[3],"is":[4],"a":[5],"critical":[6],"component":[7],"of":[8,33,50,63,111,119],"music":[9],"information":[10],"retrieval":[11],"(MIR),":[12],"aimed":[13],"at":[14],"identifying":[15],"and":[16,31,59,75,80,90,100,109,123,159,164],"classifying":[17],"instruments":[18],"from":[19],"audio":[20],"recordings.":[21],"This":[22,140],"task":[23],"poses":[24],"significant":[25],"challenges":[26],"due":[27],"to":[28,46,96],"the":[29,48,61,107],"complexity":[30],"variability":[32],"musical":[34,66,150],"signals.":[35],"Methods:":[36],"In":[37],"this":[38],"study,":[39],"we":[40],"employed":[41],"convolutional":[42],"neural":[43],"networks":[44],"(CNNs)":[45],"analyze":[47],"contributions":[49],"various":[51],"spectrogram":[52,113],"representations-STFT,":[53],"Log-Mel,":[54],"MFCC,":[55],"Chroma,":[56],"Spectral":[57],"Contrast,":[58],"Tonnetz-to":[60],"classification":[62],"ten":[64],"different":[65,120],"instruments.":[67,121],"The":[68],"NSynth":[69],"database":[70],"was":[71],"used":[72],"for":[73,149,155],"training":[74],"evaluation.":[76],"Visual":[77],"heatmap":[78],"analysis":[79,141],"statistical":[81,163],"metrics,":[82],"including":[83],"Difference":[84],"Mean,":[85],"KL":[86],"Divergence,":[87,89],"JS":[88],"Earth":[91],"Mover's":[92],"Distance,":[93],"were":[94],"utilized":[95],"assess":[97],"feature":[98],"importance":[99],"model":[101,157],"interpretability.":[102],"Results:":[103],"Our":[104],"findings":[105],"highlight":[106],"strengths":[108],"limitations":[110],"each":[112],"type":[114],"in":[115],"capturing":[116],"distinctive":[117],"features":[118],"MFCC":[122],"Log-Mel":[124],"spectrograms":[125],"demonstrated":[126],"superior":[127],"performance":[128],"across":[129],"most":[130],"instruments,":[131],"while":[132],"others":[133],"provided":[134],"insights":[135,144],"into":[136,145],"specific":[137],"characteristics.":[138],"Discussion:":[139],"provides":[142],"some":[143],"optimizing":[146],"spectrogram-based":[147],"approaches":[148],"recognition,":[152],"offering":[153],"guidance":[154],"future":[156],"development":[158],"improving":[160],"interpretability":[161],"through":[162],"visual":[165],"analyses.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}