{"id":"https://openalex.org/W3135897896","doi":"https://doi.org/10.1109/icassp39728.2021.9414551","title":"Multi-View Audio And Music Classification","display_name":"Multi-View Audio And Music Classification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3135897896","doi":"https://doi.org/10.1109/icassp39728.2021.9414551","mag":"3135897896"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2103.02420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"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":"Huy Phan","raw_affiliation_strings":["Queen Mary University of London,UK","Queen Mary, University of London (UK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary, University of London (UK)","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102936404","display_name":"Huy L. Nguy\u00ean","orcid":"https://orcid.org/0000-0001-5128-6545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Le Nguyen","raw_affiliation_strings":["HCMC University of Technology,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCMC University of Technology,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074236126","display_name":"Oliver Y. Ch\u00e9n","orcid":"https://orcid.org/0000-0002-5696-3127"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Y. Chen","raw_affiliation_strings":["University of Oxford,UK","Univ. of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Univ. of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Austrian Institute of Technology Vienna,Austria","[Austrian Institute of Technology, Vienna, Austria]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"[Austrian Institute of Technology, Vienna, Austria]","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840858","display_name":"Philipp Koch","orcid":"https://orcid.org/0000-0002-8795-758X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Koch","raw_affiliation_strings":["University of Lübeck,Germany","#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lübeck,Germany","institution_ids":[]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["Singapore Institute of Technology,Singapore","Singapore Institute of Technology , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"Singapore Institute of Technology , Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["University of Lübeck,Germany","#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lübeck,Germany","institution_ids":[]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02556308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"611","last_page":"615"},"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":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8662137985229492},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7925517559051514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767339289188385},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7090303301811218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.545133650302887},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43977296352386475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4283597469329834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37853604555130005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32247763872146606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23368924856185913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10326501727104187},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06786271929740906}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8662137985229492},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7925517559051514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767339289188385},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7090303301811218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545133650302887},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43977296352386475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4283597469329834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37853604555130005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32247763872146606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23368924856185913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10326501727104187},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06786271929740906},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.02420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02420","pdf_url":"https://arxiv.org/pdf/2103.02420","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":"mag:3135897896","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.02420.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":"pmh:oai:figshare.com:article/24217329","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Multi-view_audio_and_music_classification/24217329","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74440","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74440","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.2103.02420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.02420","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/xwrh-kz79","is_oa":true,"landing_page_url":"https://doi.org/10.17023/xwrh-kz79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},{"id":"doi:10.57702/tkxw4gql","is_oa":true,"landing_page_url":"https://doi.org/10.57702/tkxw4gql","pdf_url":null,"source":{"id":"https://openalex.org/S7407053387","display_name":"TIB Data Manager","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802635041","host_organization_name":"Technische Informationsbibliothek (TIB)","host_organization_lineage":["https://openalex.org/I2802635041"],"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":"Dataset"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.02420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02420","pdf_url":"https://arxiv.org/pdf/2103.02420","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2052666245","https://openalex.org/W2133824856","https://openalex.org/W2157331557","https://openalex.org/W2191779130","https://openalex.org/W2198584637","https://openalex.org/W2529337537","https://openalex.org/W2566935005","https://openalex.org/W2618553051","https://openalex.org/W2641889749","https://openalex.org/W2768188490","https://openalex.org/W2896911561","https://openalex.org/W2939574508","https://openalex.org/W2962711843","https://openalex.org/W2963451564","https://openalex.org/W2963546301","https://openalex.org/W2963794569","https://openalex.org/W2964121744","https://openalex.org/W2964328535","https://openalex.org/W2972247414","https://openalex.org/W2972651776","https://openalex.org/W2973157397","https://openalex.org/W3016659311","https://openalex.org/W3040939498","https://openalex.org/W3095753917","https://openalex.org/W3097525302","https://openalex.org/W3114298706","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6740195615","https://openalex.org/W6759094740","https://openalex.org/W6763597408","https://openalex.org/W6775888111","https://openalex.org/W6780397040"],"related_works":["https://openalex.org/W3161798961","https://openalex.org/W2735880737","https://openalex.org/W2526479943","https://openalex.org/W2965400859","https://openalex.org/W2071573969","https://openalex.org/W2293958442","https://openalex.org/W3100506510","https://openalex.org/W3092072146","https://openalex.org/W2594033493","https://openalex.org/W3120358876","https://openalex.org/W2562107904","https://openalex.org/W2897831002","https://openalex.org/W3108632511","https://openalex.org/W2922069550","https://openalex.org/W2903664776","https://openalex.org/W2963112418","https://openalex.org/W2768627739","https://openalex.org/W3196959210","https://openalex.org/W3149786944","https://openalex.org/W3207313418"],"abstract_inverted_index":{"We":[0],"propose":[1],"in":[2,46,119],"this":[3],"work":[4],"a":[5,61,121,126,138],"multi-view":[6,32,55,160,174],"learning":[7,97,124,136],"approach":[8],"for":[9,24,57,112],"audio":[10,25,151],"and":[11,26,103,152,179],"music":[12,27,153],"classification.":[13],"Considering":[14],"four":[15,36,76],"typical":[16],"low-level":[17],"representations":[18],"(i.e.":[19],"different":[20,150],"views)":[21],"commonly":[22],"used":[23],"recognition":[28],"tasks,":[29],"the":[30,47,54,68,72,80,84,96,100,158,165,173],"proposed":[31,91,159],"network":[33,73,113,161],"consists":[34],"of":[35,83,95],"subnetworks,":[37],"each":[38],"handling":[39],"one":[40],"input":[41],"types.":[42],"The":[43,115],"learned":[44],"embedding":[45,56,82],"subnetworks":[48],"are":[49,117],"then":[50,90],"concatenated":[51],"to":[52,60,92,107,172],"form":[53],"classification":[58,70,77,101,154],"similar":[59],"simple":[62],"concatenation":[63,178],"network.":[64],"However,":[65],"apart":[66],"from":[67],"joint":[69],"branch,":[71],"also":[74,169],"maintains":[75],"branches":[78,102],"on":[79,99,125,137,148,177],"single-view":[81,166],"subnetworks.":[85],"A":[86],"novel":[87],"method":[88],"is":[89,129,141,170],"keep":[93],"track":[94],"behavior":[98],"adapt":[104],"their":[105,110],"weights":[106,116],"proportionally":[108],"blend":[109],"gradients":[111],"training.":[114],"adapted":[118],"such":[120],"way":[122],"that":[123,128,140,157],"branch":[127,139],"generalizing":[130],"well":[131],"will":[132,143],"be":[133,144],"encouraged":[134],"whereas":[135],"overfitting":[142],"slowed":[145],"down.":[146],"Experiments":[147],"three":[149],"tasks":[155],"show":[156],"not":[162],"only":[163],"outperforms":[164],"baselines":[167,175],"but":[168],"superior":[171],"based":[176],"late":[180],"fusion.":[181]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}