{"id":"https://openalex.org/W2437181147","doi":"https://doi.org/10.1109/cbmi.2016.7500246","title":"Experimenting with musically motivated convolutional neural networks","display_name":"Experimenting with musically motivated convolutional neural networks","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2437181147","doi":"https://doi.org/10.1109/cbmi.2016.7500246","mag":"2437181147"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi.2016.7500246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2016.7500246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"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/A5023691144","display_name":"Thomas Lidy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT","CN"],"is_corresponding":false,"raw_author_name":"Thomas Lidy","raw_affiliation_strings":["TU Wien, Institute of Software Technology and Interactive Systems"],"affiliations":[{"raw_affiliation_string":"TU Wien, Institute of Software Technology and Interactive Systems","institution_ids":["https://openalex.org/I145847075","https://openalex.org/I4210128818"]}]},{"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":"Pompeu Fabra University","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"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103137809"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":15.383,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99309277,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9958000183105469,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.7814938426017761},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7033354043960571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46576690673828125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42689943313598633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814938426017761},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7033354043960571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46576690673828125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42689943313598633}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cbmi.2016.7500246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2016.7500246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/27038","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/27038","pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/acceptedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1721549435","https://openalex.org/W1790748249","https://openalex.org/W1849277567","https://openalex.org/W2016043834","https://openalex.org/W2042390666","https://openalex.org/W2045135321","https://openalex.org/W2059652044","https://openalex.org/W2074619556","https://openalex.org/W2095705004","https://openalex.org/W2110485445","https://openalex.org/W2112796928","https://openalex.org/W2149590880","https://openalex.org/W2240580723","https://openalex.org/W2242773987","https://openalex.org/W2286647287","https://openalex.org/W2294252515","https://openalex.org/W2406222150","https://openalex.org/W2408401389","https://openalex.org/W3124794156","https://openalex.org/W4254816979","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6690079499","https://openalex.org/W6690394000","https://openalex.org/W6695636578","https://openalex.org/W6697413020","https://openalex.org/W6713612469"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"A":[0],"common":[1],"criticism":[2],"of":[3,34,85,93,101,104,163],"deep":[4,87,153],"learning":[5,88,126,154],"relates":[6],"to":[7,43,149],"the":[8,12,16,47,83,86,91,122],"difficulty":[9],"in":[10,41,90,109],"understanding":[11,45],"underlying":[13],"relationships":[14],"that":[15,69],"neural":[17],"networks":[18,49],"are":[19,50,78,125],"learning,":[20],"thus":[21],"behaving":[22],"like":[23],"a":[24,98,113,132,138,160],"black-box.":[25],"In":[26],"this":[27,110],"article":[28],"we":[29,70,145],"explore":[30],"various":[31,94],"architectural":[32],"choices":[33],"relevance":[35],"for":[36,140],"music":[37,95],"signals":[38],"classification":[39],"tasks":[40],"order":[42],"start":[44],"what":[46,118,151],"chosen":[48],"learning.":[51],"We":[52],"first":[53],"discuss":[54],"how":[55],"convolutional":[56],"filters":[57],"with":[58,116],"different":[59],"shapes":[60],"can":[61,157],"fit":[62],"specific":[63],"musical":[64],"concepts":[65],"and":[66],"based":[67,155],"on":[68],"propose":[71],"several":[72],"musically":[73],"motivated":[74],"architectures.":[75],"These":[76],"architectures":[77,124],"then":[79],"assessed":[80],"by":[81],"measuring":[82],"accuracy":[84],"model":[89,134],"prediction":[92],"classes":[96,108],"using":[97],"known":[99],"dataset":[100,111],"audio":[102],"recordings":[103],"ballroom":[105],"music.":[106],"The":[107],"have":[112,146],"strong":[114],"correlation":[115],"tempo,":[117],"allows":[119],"assessing":[120],"if":[121],"proposed":[123,136],"frequency":[127],"and/or":[128],"time":[129],"dependencies.":[130],"Additionally,":[131],"black-box":[133],"is":[135],"as":[137],"baseline":[139],"comparison.":[141],"With":[142],"these":[143],"experiments":[144],"been":[147],"able":[148],"understand":[150],"some":[152],"algorithms":[156],"learn":[158],"from":[159],"particular":[161],"set":[162],"data.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}