{"id":"https://openalex.org/W4224918495","doi":"https://doi.org/10.1109/icassp43922.2022.9747467","title":"Ambiguity Modelling with Label Distribution Learning for Music Classification","display_name":"Ambiguity Modelling with Label Distribution Learning for Music Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918495","doi":"https://doi.org/10.1109/icassp43922.2022.9747467"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747467","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087112013","display_name":"Morgan Buisson","orcid":"https://orcid.org/0000-0001-8541-3071"},"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":"Morgan Buisson","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group","Music Technology Group, Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085164793","display_name":"Pablo Alonso-Jim\u00e9nez","orcid":"https://orcid.org/0000-0002-4121-5089"},"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":"Pablo Alonso-Jimenez","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group","Music Technology Group, Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","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":["Universitat Pompeu Fabra,Music Technology Group","Music Technology Group, Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.5537,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58762036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9987000226974487,"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":0.9940000176429749,"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":0.7806830406188965},{"id":"https://openalex.org/keywords/vagueness","display_name":"Vagueness","score":0.6933375000953674},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6695781946182251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5707255601882935},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5563153028488159},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5445159077644348},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5277923941612244},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5243192911148071},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5168029069900513},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4731113612651825},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4714059829711914},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.46936777234077454},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.45256972312927246},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42226916551589966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33655035495758057},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.16026782989501953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07466152310371399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806830406188965},{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.6933375000953674},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6695781946182251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5707255601882935},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5563153028488159},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5445159077644348},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5277923941612244},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5243192911148071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5168029069900513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4731113612651825},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4714059829711914},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.46936777234077454},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.45256972312927246},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42226916551589966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33655035495758057},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.16026782989501953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07466152310371399},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747467","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/53294","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/53294","pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2873872","https://openalex.org/W56995320","https://openalex.org/W1606285668","https://openalex.org/W2046554054","https://openalex.org/W2059652044","https://openalex.org/W2066454034","https://openalex.org/W2101151533","https://openalex.org/W2106053110","https://openalex.org/W2133824856","https://openalex.org/W2178339699","https://openalex.org/W2330485005","https://openalex.org/W2341090665","https://openalex.org/W2396710586","https://openalex.org/W2414894569","https://openalex.org/W2437181147","https://openalex.org/W2526050071","https://openalex.org/W2553156677","https://openalex.org/W2783599290","https://openalex.org/W2808535973","https://openalex.org/W2950060770","https://openalex.org/W2963451564","https://openalex.org/W2968396469","https://openalex.org/W2972737975","https://openalex.org/W3015310419","https://openalex.org/W3047712904","https://openalex.org/W3105198788","https://openalex.org/W3105616927","https://openalex.org/W4286850225","https://openalex.org/W4287642684","https://openalex.org/W6600120404","https://openalex.org/W6602337844","https://openalex.org/W6636384021","https://openalex.org/W6675751002","https://openalex.org/W6704344484","https://openalex.org/W6712494662","https://openalex.org/W6715395060","https://openalex.org/W6752180941","https://openalex.org/W6763945542","https://openalex.org/W6768465061","https://openalex.org/W6803752119"],"related_works":["https://openalex.org/W2496023037","https://openalex.org/W2350451705","https://openalex.org/W4213284915","https://openalex.org/W4212798463","https://openalex.org/W2974127468","https://openalex.org/W2366109760","https://openalex.org/W2340041618","https://openalex.org/W2950081262","https://openalex.org/W1524077593","https://openalex.org/W2078120539"],"abstract_inverted_index":{"An":[0],"important":[1],"amount":[2],"of":[3,11,47,96],"work":[4],"has":[5],"been":[6],"devoted":[7],"to":[8,28,34,74,119],"the":[9,45,106,113],"task":[10],"music":[12,97,136],"classification.":[13],"Despite":[14],"promising":[15],"results":[16],"achieved":[17],"by":[18,129],"convolutional":[19],"neural":[20],"networks,":[21],"there":[22],"still":[23],"exists":[24],"a":[25,58,94],"gap":[26],"left":[27],"be":[29,132],"filled":[30],"for":[31,90],"such":[32],"models":[33],"perform":[35],"well":[36],"in":[37,52,133],"real-world":[38],"applications.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"address":[44],"issue":[46],"ambiguity":[48],"that":[49,65,105],"can":[50,131],"arise":[51],"many":[53],"classification":[54,92,101,137],"problems.":[55],"We":[56,81,103],"propose":[57],"method":[59,84],"based":[60],"on":[61,93],"adaptive":[62],"label":[63],"smoothing":[64],"aims":[66],"at":[67],"implicitly":[68],"modelling":[69],"perceptual":[70],"vagueness":[71],"among":[72],"classes":[73],"improve":[75],"both":[76],"training":[77],"and":[78,99,123],"testing":[79],"performances.":[80],"assess":[82],"our":[83],"using":[85],"two":[86],"state-of-the-art":[87],"CNN":[88],"architectures":[89],"audio":[91,121],"variety":[95],"mood":[98],"genre":[100],"tasks.":[102],"show":[104],"proposed":[107],"strategy":[108],"brings":[109],"consistent":[110],"improvements":[111],"over":[112],"traditional":[114],"approach,":[115],"significantly":[116],"improves":[117],"generalization":[118],"external":[120],"collections":[122],"emphasizes":[124],"how":[125],"crucial":[126],"information":[127],"carried":[128],"labels":[130],"an":[134],"ambiguous":[135],"context.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}