{"id":"https://openalex.org/W3038063530","doi":"https://doi.org/10.23919/eusipco47968.2020.9287769","title":"How Low Can You Go? Reducing Frequency and Time Resolution in Current CNN Architectures for Music Auto-tagging","display_name":"How Low Can You Go? Reducing Frequency and Time Resolution in Current CNN Architectures for Music Auto-tagging","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3038063530","doi":"https://doi.org/10.23919/eusipco47968.2020.9287769","mag":"3038063530"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287769","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.04824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050623835","display_name":"Andr\u00e9s Ferraro","orcid":"https://orcid.org/0000-0003-1236-2503"},"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":"Andres Ferraro","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633"},"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":"Dmitry Bogdanov","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","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 Jay","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492531","display_name":"Jay Ho Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114081","display_name":"Korea Kacoh (South Korea)","ror":"https://ror.org/02930yz47","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210114081"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho Jeon","raw_affiliation_strings":["Kakao Corp, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Corp, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210114081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023226995","display_name":"Jason Yoon","orcid":"https://orcid.org/0009-0007-9073-4516"},"institutions":[{"id":"https://openalex.org/I4210114081","display_name":"Korea Kacoh (South Korea)","ror":"https://ror.org/02930yz47","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210114081"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jason Yoon","raw_affiliation_strings":["Kakao Corp, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Corp, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210114081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.06181215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"135"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9952999949455261,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9876000285148621,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8955126404762268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.763184666633606},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7062525749206543},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6726032495498657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6235734224319458},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5324956178665161},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5201123952865601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5093532800674438},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5088613033294678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5013964176177979},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44136661291122437},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4376176595687866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3869098126888275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3314288556575775},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2378527820110321},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.19882631301879883},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11713704466819763},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09174719452857971}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8955126404762268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763184666633606},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7062525749206543},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6726032495498657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6235734224319458},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5324956178665161},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5201123952865601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5093532800674438},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5088613033294678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013964176177979},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44136661291122437},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4376176595687866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3869098126888275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3314288556575775},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2378527820110321},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.19882631301879883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11713704466819763},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09174719452857971},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287769","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.04824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04824","pdf_url":"https://arxiv.org/pdf/1911.04824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repositori.upf.edu:10230/56074","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/56074","pdf_url":"https://repositori.upf.edu/bitstreams/2b941c80-7e55-42be-9cd5-beab2ae3d781/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"},{"id":"mag:3038063530","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.04824.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.04824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.04824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.04824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04824","pdf_url":"https://arxiv.org/pdf/1911.04824","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2385545","https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W1686810756","https://openalex.org/W1950706092","https://openalex.org/W1976526581","https://openalex.org/W2059652044","https://openalex.org/W2127870748","https://openalex.org/W2137637927","https://openalex.org/W2583165630","https://openalex.org/W2593179621","https://openalex.org/W2604509013","https://openalex.org/W2756184659","https://openalex.org/W2774685635","https://openalex.org/W2890267272","https://openalex.org/W2955425717","https://openalex.org/W2962813390","https://openalex.org/W2963181423","https://openalex.org/W2963369619","https://openalex.org/W2963451564","https://openalex.org/W2964285380","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640824186","https://openalex.org/W6678969435","https://openalex.org/W6715395060","https://openalex.org/W6734751391","https://openalex.org/W6741185346","https://openalex.org/W6744511850","https://openalex.org/W6745878906","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W2983429460","https://openalex.org/W2767858146","https://openalex.org/W2803417255","https://openalex.org/W3154102786","https://openalex.org/W3012522686","https://openalex.org/W2939753704","https://openalex.org/W3130204614","https://openalex.org/W2896271387","https://openalex.org/W3169982272","https://openalex.org/W3011915764","https://openalex.org/W3209097778","https://openalex.org/W3098670224","https://openalex.org/W3113346801","https://openalex.org/W2911113553","https://openalex.org/W2784180354","https://openalex.org/W2902208587","https://openalex.org/W2604509013","https://openalex.org/W2910489255","https://openalex.org/W3009078343","https://openalex.org/W3006292378"],"abstract_inverted_index":{"Automatic":[0],"tagging":[1],"of":[2,43,70,74,103,117],"music":[3],"is":[4],"an":[5],"important":[6],"research":[7],"topic":[8],"in":[9,26,68,111],"Music":[10],"Information":[11],"Retrieval":[12],"and":[13,38,55,77,90,109,123,125],"audio":[14],"analysis":[15],"algorithms":[16],"proposed":[17],"for":[18,86],"this":[19,47,104],"task":[20],"have":[21],"achieved":[22,62],"improvements":[23],"with":[24],"advances":[25],"deep":[27],"learning.":[28],"In":[29,46],"particular,":[30],"many":[31],"state-of-the-art":[32],"systems":[33],"use":[34,82],"Convolutional":[35],"Neural":[36],"Networks":[37],"operate":[39],"on":[40,95],"mel-spectrogram":[41,53],"representations":[42,54],"the":[44,65,83,96,118],"audio.":[45],"paper,":[48],"we":[49],"compare":[50,92],"commonly":[51],"used":[52],"evaluate":[56],"model":[57],"performances":[58],"that":[59],"can":[60,106],"be":[61],"by":[63],"reducing":[64],"input":[66],"size":[67,122],"terms":[69],"both":[71],"lesser":[72],"amount":[73],"frequency":[75],"bands":[76],"larger":[78,97],"frame":[79],"rates.":[80],"We":[81],"MagnaTagaTune":[84],"dataset":[85],"comprehensive":[87],"performance":[88],"comparisons":[89],"then":[91],"selected":[93],"configurations":[94],"Million":[98],"Song":[99],"Dataset.":[100],"The":[101],"results":[102],"study":[105],"serve":[107],"researchers":[108],"practitioners":[110],"their":[112],"trade-off":[113],"decision":[114],"between":[115],"accuracy":[116],"models,":[119],"data":[120],"storage":[121],"training":[124],"inference":[126],"times.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-07-26T00:00:00"}