{"id":"https://openalex.org/W2963451564","doi":"https://doi.org/10.1109/icassp.2017.7952585","title":"Convolutional recurrent neural networks for music classification","display_name":"Convolutional recurrent neural networks for music classification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2963451564","doi":"https://doi.org/10.1109/icassp.2017.7952585","mag":"2963451564"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5011038627","display_name":"Keunwoo Choi","orcid":"https://orcid.org/0000-0002-5305-5342"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Keunwoo Choi","raw_affiliation_strings":["EECS, Centre for Digital Music, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS, Centre for Digital Music, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyorgy Fazekas","raw_affiliation_strings":["EECS, Centre for Digital Music, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS, Centre for Digital Music, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076173089","display_name":"M. Sandler","orcid":"https://orcid.org/0000-0002-5691-8107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Sandler","raw_affiliation_strings":["EECS, Centre for Digital Music, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS, Centre for Digital Music, London, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091175785","display_name":"Kyunghyun Cho","orcid":"https://orcid.org/0000-0003-1669-3211"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["Computer Science & Data Science, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Data Science, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011038627"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.2157,"has_fulltext":false,"cited_by_count":487,"citation_normalized_percentile":{"value":0.99863444,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2392","last_page":"2396"},"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":0.996999979019165,"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":0.9965000152587891,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8292787075042725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7838457822799683},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6983628273010254},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6805208325386047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5936387181282043},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5772963762283325},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5418731570243835},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4319548010826111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36522847414016724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.346011757850647}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8292787075042725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838457822799683},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6983628273010254},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6805208325386047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936387181282043},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5772963762283325},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5418731570243835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4319548010826111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36522847414016724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.346011757850647},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8217561489","display_name":null,"funder_award_id":"EP/L019981/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W1836465849","https://openalex.org/W1922658220","https://openalex.org/W2059652044","https://openalex.org/W2071103260","https://openalex.org/W2095705004","https://openalex.org/W2137028279","https://openalex.org/W2191779130","https://openalex.org/W2198584637","https://openalex.org/W2250966211","https://openalex.org/W2253400648","https://openalex.org/W2293924895","https://openalex.org/W2340134902","https://openalex.org/W2384495648","https://openalex.org/W2397811227","https://openalex.org/W2414894569","https://openalex.org/W2461724944","https://openalex.org/W2575145750","https://openalex.org/W2963285578","https://openalex.org/W2963369619","https://openalex.org/W2964199361","https://openalex.org/W6674330103","https://openalex.org/W6704025895","https://openalex.org/W6715395060"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2578422401"],"abstract_inverted_index":{"We":[0,34],"introduce":[1],"a":[2,70],"convolutional":[3,15],"recurrent":[4,24],"neural":[5,16,25],"network":[6],"(CRNN)":[7],"for":[8,19,27,45],"music":[9,46,91],"tagging.":[10],"CRNNs":[11,68],"take":[12],"advantage":[13],"of":[14,30,52,78,86],"networks":[17,26],"(CNNs)":[18],"local":[20],"feature":[21,92,95],"extraction":[22,93],"and":[23,59,80,94],"temporal":[28],"summarisation":[29],"the":[31,50,76,84],"extracted":[32],"features.":[33],"compare":[35],"CRNN":[36],"with":[37,54,73],"three":[38],"CNN":[39],"structures":[40],"that":[41,67],"have":[42],"been":[43],"used":[44],"tagging":[47],"while":[48],"controlling":[49],"number":[51,77],"parameters":[53],"respect":[55,74],"to":[56,75],"their":[57],"performance":[58,72],"training":[60,81],"time":[61],"per":[62],"sample.":[63],"Overall,":[64],"we":[65],"found":[66],"show":[69],"strong":[71],"parameter":[79],"time,":[82],"indicating":[83],"effectiveness":[85],"its":[87],"hybrid":[88],"structure":[89],"in":[90],"summarisation.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":64},{"year":2022,"cited_by_count":63},{"year":2021,"cited_by_count":79},{"year":2020,"cited_by_count":62},{"year":2019,"cited_by_count":79},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":16}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}