{"id":"https://openalex.org/W3015289235","doi":"https://doi.org/10.1109/icassp40776.2020.9053669","title":"Data-Driven Harmonic Filters for Audio Representation Learning","display_name":"Data-Driven Harmonic Filters for Audio Representation Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015289235","doi":"https://doi.org/10.1109/icassp40776.2020.9053669","mag":"3015289235"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/078de1cc-7526-4f17-9ec1-10e3c29a01fc/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"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":true,"raw_author_name":"Minz Won","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"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/A5067167236","display_name":"Sanghyuk Chun","orcid":"https://orcid.org/0000-0002-4533-2610"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyuk Chun","raw_affiliation_strings":["Clova AI Research, NAVER Corp., Seongnam, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Clova AI Research, NAVER Corp., Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Pandora Media Inc., Oakland, CA, United States of America"],"affiliations":[{"raw_affiliation_string":"Pandora Media Inc., Oakland, CA, United States of America","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057588664","display_name":"Xavier Serrc","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":"Xavier Serrc","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041096205"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":5.1737,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96449511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"540"},"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415555715560913},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.678246796131134},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6146199107170105},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.6028820276260376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5756611824035645},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5425930023193359},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5053215622901917},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5047100782394409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4122140109539032},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2002517282962799},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12234780192375183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415555715560913},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.678246796131134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6146199107170105},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.6028820276260376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5756611824035645},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5425930023193359},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5053215622901917},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5047100782394409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122140109539032},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2002517282962799},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12234780192375183},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/44278","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/44278","pdf_url":"https://repositori.upf.edu/bitstreams/078de1cc-7526-4f17-9ec1-10e3c29a01fc/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:10230/44278","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/44278","pdf_url":"https://repositori.upf.edu/bitstreams/078de1cc-7526-4f17-9ec1-10e3c29a01fc/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":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015289235.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W2050758723","https://openalex.org/W2127870748","https://openalex.org/W2398826216","https://openalex.org/W2529337537","https://openalex.org/W2593116425","https://openalex.org/W2593179621","https://openalex.org/W2658929981","https://openalex.org/W2751116311","https://openalex.org/W2767858146","https://openalex.org/W2773294482","https://openalex.org/W2775505379","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2891171253","https://openalex.org/W2935162632","https://openalex.org/W2952395326","https://openalex.org/W2962813390","https://openalex.org/W2962923973","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W3003890830","https://openalex.org/W3028311979","https://openalex.org/W4298366219","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6640090968","https://openalex.org/W6678969435","https://openalex.org/W6712560600","https://openalex.org/W6728126488","https://openalex.org/W6734260513","https://openalex.org/W6734751391","https://openalex.org/W6739890979","https://openalex.org/W6743647910","https://openalex.org/W6745878906","https://openalex.org/W6746836464","https://openalex.org/W6747331233","https://openalex.org/W6750665317","https://openalex.org/W6754802931","https://openalex.org/W6760192491","https://openalex.org/W6764574124","https://openalex.org/W6773440759"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2088690926","https://openalex.org/W1526651343","https://openalex.org/W4387698063"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,24,48,71],"trainable":[3],"front-end":[4,80],"module":[5],"for":[6],"audio":[7,17,65],"representation":[8],"learning":[9],"that":[10,70],"exploits":[11],"the":[12,29,41,78],"inherent":[13],"harmonic":[14,34,42,59],"structure":[15,43],"of":[16,23,26],"signals.":[18],"The":[19],"proposed":[20,79],"architecture,":[21],"composed":[22],"set":[25],"filters,":[27],"compels":[28],"subsequent":[30],"network":[31,75],"to":[32,46,61],"capture":[33],"relations":[35],"while":[36],"preserving":[37],"spectro-temporal":[38],"locality.":[39],"Since":[40],"is":[44],"known":[45],"have":[47],"key":[49],"role":[50],"in":[51,85],"human":[52],"auditory":[53],"perception,":[54],"one":[55],"can":[56],"expect":[57],"these":[58],"filters":[60],"yield":[62],"more":[63],"efficient":[64],"representations.":[66],"Experimental":[67],"results":[68],"show":[69],"simple":[72],"convolutional":[73],"neural":[74],"back-end":[76],"with":[77],"outperforms":[81],"state-of-the-art":[82],"baseline":[83],"methods":[84],"automatic":[86],"music":[87],"tagging,":[88],"keyword":[89],"spotting,":[90],"and":[91],"sound":[92],"event":[93],"tagging":[94],"tasks.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-11T06:13:24.991567","created_date":"2025-10-10T00:00:00"}