{"id":"https://openalex.org/W2604509013","doi":"https://doi.org/10.23919/eusipco.2017.8081710","title":"Timbre analysis of music audio signals with convolutional neural networks","display_name":"Timbre analysis of music audio signals with convolutional neural networks","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2604509013","doi":"https://doi.org/10.23919/eusipco.2017.8081710","mag":"2604509013"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2017.8081710","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/ab3c5ad4-4c47-443a-8221-3769effe03fa/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061474153","display_name":"Olga Slizovskaia","orcid":"https://orcid.org/0000-0003-3118-5143"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Olga Slizovskaia","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027977314","display_name":"Em\u00edlia G\u00f3mez","orcid":"https://orcid.org/0000-0003-4983-3989"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Emilia Gomez","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":8.2029,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.98300133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2744","last_page":"2748"},"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/timbre","display_name":"Timbre","score":0.9606815576553345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115328550338745},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7907443642616272},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6397749781608582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6296785473823547},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.556688129901886},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5397684574127197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44810715317726135},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4300971031188965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4263615012168884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3441123366355896},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.16218504309654236}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9606815576553345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115328550338745},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7907443642616272},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6397749781608582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6296785473823547},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.556688129901886},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5397684574127197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44810715317726135},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4300971031188965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4263615012168884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3441123366355896},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.16218504309654236},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco.2017.8081710","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/33998","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/33998","pdf_url":"https://repositori.upf.edu/bitstreams/ab3c5ad4-4c47-443a-8221-3769effe03fa/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositori.upf.edu:10230/33998","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/33998","pdf_url":"https://repositori.upf.edu/bitstreams/ab3c5ad4-4c47-443a-8221-3769effe03fa/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2604509013.pdf","grobid_xml":"https://content.openalex.org/works/W2604509013.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W123034841","https://openalex.org/W1590102137","https://openalex.org/W1601892841","https://openalex.org/W1677182931","https://openalex.org/W1781845406","https://openalex.org/W1836465849","https://openalex.org/W2008066450","https://openalex.org/W2059652044","https://openalex.org/W2079080230","https://openalex.org/W2107789863","https://openalex.org/W2125838338","https://openalex.org/W2127870748","https://openalex.org/W2176412452","https://openalex.org/W2410860376","https://openalex.org/W2414894569","https://openalex.org/W2437181147","https://openalex.org/W2583165630","https://openalex.org/W2963158330","https://openalex.org/W2963285578","https://openalex.org/W2963369619","https://openalex.org/W3098670224","https://openalex.org/W6635274319","https://openalex.org/W6638109833","https://openalex.org/W6638667902","https://openalex.org/W6676071220","https://openalex.org/W6678969435","https://openalex.org/W6715395060"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W3016250102","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"The":[0],"focus":[1],"of":[2,82,97,105],"this":[3,34,54],"work":[4],"is":[5,86,107],"to":[6,9,44,62,87,100,126],"study":[7],"how":[8],"efficiently":[10,47],"tailor":[11],"Convolutional":[12],"Neural":[13],"Networks":[14],"(CNNs)":[15],"towards":[16],"learning":[17,48,69],"timbre":[18,49],"representations":[19,50],"from":[20],"log-mel":[21],"magnitude":[22],"spectrograms.":[23],"We":[24],"first":[25],"review":[26],"the":[27,41,64,95,113],"trends":[28],"when":[29],"designing":[30,77],"CNN":[31,90],"architectures.":[32,78],"Through":[33],"literature":[35],"overview":[36],"we":[37,56,116],"discuss":[38],"which":[39,71],"are":[40,118],"crucial":[42],"points":[43],"consider":[45],"for":[46,68,76,121],"using":[51,73],"CNNs.":[52],"From":[53],"discussion":[55],"propose":[57,117],"a":[58],"design":[59,88,114],"strategy":[60],"meant":[61],"capture":[63],"relevant":[65],"time-frequency":[66],"contexts":[67],"timbre,":[70],"permits":[72],"domain":[74],"knowledge":[75],"In":[79],"addition,":[80],"one":[81],"our":[83],"main":[84],"goals":[85],"efficient":[89],"architectures":[91,110],"-":[92],"what":[93],"reduces":[94],"risk":[96],"these":[98],"models":[99],"over-fit,":[101],"since":[102],"CNNs'":[103],"number":[104],"parameters":[106],"minimized.":[108],"Several":[109],"based":[111],"on":[112],"principles":[115],"successfully":[119],"assessed":[120],"different":[122],"research":[123],"tasks":[124],"related":[125],"timbre:":[127],"singing":[128],"voice":[129],"phoneme":[130],"classification,":[131],"musical":[132],"instrument":[133],"recognition":[134],"and":[135],"music":[136],"auto-tagging.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}