{"id":"https://openalex.org/W3164719166","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533547","title":"A Modulation Front-End for Music Audio Tagging","display_name":"A Modulation Front-End for Music Audio Tagging","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3164719166","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533547","mag":"3164719166"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.11836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091632784","display_name":"Cyrus Vahidi","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Cyrus Vahidi","raw_affiliation_strings":["Centre for Digital Music Queen Mary University of London, London, United Kingdom","Centre for Digital Music, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083980012","display_name":"Charalampos Saitis","orcid":"https://orcid.org/0000-0002-6860-9723"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Charalampos Saitis","raw_affiliation_strings":["Centre for Digital Music Queen Mary University of London, London, United Kingdom","Centre for Digital Music, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gyorgy Fazekas","raw_affiliation_strings":["Centre for Digital Music Queen Mary University of London, London, United Kingdom","Centre for Digital Music, Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091632784"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05309971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9957000017166138,"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":0.7739434838294983},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6990207433700562},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6224778890609741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.620295524597168},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6010347604751587},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5376155972480774},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.48171836137771606},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4557774066925049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44871431589126587},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.447637140750885},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4363346993923187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35980668663978577},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2223561406135559},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19288358092308044},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.11004665493965149},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08946743607521057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739434838294983},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6990207433700562},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6224778890609741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.620295524597168},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6010347604751587},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5376155972480774},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.48171836137771606},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4557774066925049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44871431589126587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.447637140750885},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4363346993923187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35980668663978577},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2223561406135559},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19288358092308044},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.11004665493965149},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08946743607521057},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.11836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11836","pdf_url":"https://arxiv.org/pdf/2105.11836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3164719166","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2105.11836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:qmro.qmul.ac.uk:123456789/72389","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/72389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"doi:10.48550/arxiv.2105.11836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.11836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.11836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11836","pdf_url":"https://arxiv.org/pdf/2105.11836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164719166.pdf","grobid_xml":"https://content.openalex.org/works/W3164719166.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2020775772","https://openalex.org/W2045135321","https://openalex.org/W2046331056","https://openalex.org/W2054139811","https://openalex.org/W2059652044","https://openalex.org/W2127618892","https://openalex.org/W2127870748","https://openalex.org/W2331927446","https://openalex.org/W2398826216","https://openalex.org/W2502312327","https://openalex.org/W2504258391","https://openalex.org/W2553581788","https://openalex.org/W2604509013","https://openalex.org/W2607413337","https://openalex.org/W2774685635","https://openalex.org/W2794150026","https://openalex.org/W2799958557","https://openalex.org/W2931364255","https://openalex.org/W2944398172","https://openalex.org/W2949117887","https://openalex.org/W2962813390","https://openalex.org/W2962901777","https://openalex.org/W2963669405","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2964285380","https://openalex.org/W3003890830","https://openalex.org/W3004940340","https://openalex.org/W3015289235","https://openalex.org/W3029858316","https://openalex.org/W3124414150","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6678969435","https://openalex.org/W6712560600","https://openalex.org/W6724804524","https://openalex.org/W6745878906","https://openalex.org/W6778572914","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W3201535109","https://openalex.org/W3015289235","https://openalex.org/W1951918885","https://openalex.org/W3207444892","https://openalex.org/W2771726741","https://openalex.org/W2101306231","https://openalex.org/W3179030250","https://openalex.org/W2766465839","https://openalex.org/W3197621271","https://openalex.org/W1521144119","https://openalex.org/W2976594877","https://openalex.org/W2914485273","https://openalex.org/W1858125052","https://openalex.org/W2963237661","https://openalex.org/W2809039503","https://openalex.org/W3177013509","https://openalex.org/W2894295011","https://openalex.org/W3090288500","https://openalex.org/W2136936573","https://openalex.org/W3009355670"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"have":[3,35,45],"been":[4,36],"extensively":[5],"explored":[6],"in":[7,93,191],"the":[8,46,50,86,133,139,145,150,163,192],"task":[9],"of":[10,52,128,135,141,194],"automatic":[11],"music":[12,113,142,180],"tagging.":[13],"The":[14,75,97],"problem":[15],"can":[16,106],"be":[17],"approached":[18],"by":[19,162],"using":[20,186],"either":[21],"engineered":[22],"time-frequency":[23,158],"features":[24],"or":[25],"raw":[26,129],"audio":[27,62],"as":[28,39],"input.":[29],"Modulation":[30],"filter":[31,83,88,104],"bank":[32,105],"representations":[33],"that":[34,68,100,173],"actively":[37],"researched":[38],"a":[40,70,81,94,101,108,119,167],"basis":[41],"for":[42,61,111,154,179],"timbre":[43],"perception":[44],"potential":[47],"to":[48,80],"facilitate":[49],"extraction":[51],"perceptually":[53,102],"salient":[54],"features.":[55,114],"We":[56,131,148,171],"explore":[57],"end-to-end":[58],"learned":[59,92],"front-ends":[60],"representation":[63,110],"learning,":[64],"ModNet":[65],"and":[66,122,182],"SincModNet,":[67],"incorporate":[69],"temporal":[71,125],"modulation":[72,82,126,164,174],"processing":[73],"block.":[74],"structure":[76],"is":[77,99],"effectively":[78],"analogous":[79],"bank,":[84],"where":[85],"FIR":[87],"center":[89],"frequencies":[90],"are":[91,160],"data-driven":[95],"manner.":[96],"expectation":[98],"motivated":[103],"provide":[107,118],"useful":[109],"identifying":[112],"Our":[115],"experimental":[116],"results":[117,178],"fully":[120],"visualisable":[121],"interpretable":[123],"front-end":[124],"decomposition":[127],"audio.":[130],"evaluate":[132],"performance":[134,153],"our":[136],"model":[137],"against":[138],"state-of-the-art":[140],"tagging":[143,181],"on":[144,152],"MagnaTagATune":[146],"dataset.":[147],"analyse":[149],"impact":[151],"particular":[155],"tags":[156],"when":[157],"bands":[159],"subsampled":[161],"filters":[165],"at":[166],"progressively":[168],"reduced":[169],"rate.":[170],"demonstrate":[172],"filtering":[175],"provides":[176],"promising":[177],"feature":[183],"representation,":[184],"without":[185],"extensive":[187],"musical":[188],"domain":[189],"knowledge":[190],"design":[193],"this":[195],"frontend.":[196]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
