{"id":"https://openalex.org/W4372347384","doi":"https://doi.org/10.1109/icassp49357.2023.10094706","title":"Self-Supervised Learning of Audio Representations using Angular Contrastive Loss","display_name":"Self-Supervised Learning of Audio Representations using Angular Contrastive Loss","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347384","doi":"https://doi.org/10.1109/icassp49357.2023.10094706"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100406235","display_name":"Shanshan Wang","orcid":"https://orcid.org/0000-0001-9530-6958"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113833059","display_name":"Soumya Tripathy","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Soumya Tripathy","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100406235"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":1.2226,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78748044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9940000176429749,"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":0.987500011920929,"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/discriminative-model","display_name":"Discriminative model","score":0.7296343445777893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6874837279319763},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6448091268539429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5767303109169006},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5652856230735779},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5576265454292297},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5043658018112183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.499927282333374},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44350486993789673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4135705828666687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3733379542827606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1334545612335205}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7296343445777893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874837279319763},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6448091268539429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5767303109169006},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5652856230735779},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5576265454292297},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5043658018112183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.499927282333374},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44350486993789673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4135705828666687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3733379542827606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1334545612335205},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2016053056","https://openalex.org/W2123843894","https://openalex.org/W2194775991","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2900595477","https://openalex.org/W2936774411","https://openalex.org/W2963859210","https://openalex.org/W3018349615","https://openalex.org/W3137857706","https://openalex.org/W3162391496","https://openalex.org/W3175593095","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4281663607","https://openalex.org/W4287608901","https://openalex.org/W6774314701","https://openalex.org/W6778102432","https://openalex.org/W6784333009","https://openalex.org/W6785011006"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4309346246","https://openalex.org/W2515319207"],"abstract_inverted_index":{"In":[0],"Self-Supervised":[1],"Learning":[2],"(SSL),":[3],"various":[4],"pretext":[5],"tasks":[6],"are":[7],"designed":[8],"for":[9,107],"learning":[10,86,112],"feature":[11,47,59],"representations":[12],"through":[13],"contrastive":[14,81,85],"loss.":[15,82],"However,":[16],"previous":[17],"studies":[18],"have":[19],"shown":[20],"that":[21,104],"this":[22],"loss":[23,67,120],"is":[24],"less":[25],"tolerant":[26],"to":[27,32],"semantically":[28],"similar":[29],"samples":[30],"due":[31],"the":[33,43,55,123],"inherent":[34],"defect":[35],"of":[36,45,58,77],"instance":[37],"discrimination":[38],"objectives,":[39],"which":[40],"may":[41],"harm":[42],"quality":[44],"learned":[46],"embeddings":[48,60],"used":[49],"in":[50,61,99,133],"downstream":[51],"tasks.":[52],"To":[53],"improve":[54],"discriminative":[56],"ability":[57],"SSL,":[62],"we":[63,127],"propose":[64],"a":[65,74],"new":[66,119],"function":[68,121],"called":[69],"Angular":[70],"Contrastive":[71],"Loss":[72],"(ACL),":[73],"linear":[75],"combination":[76],"angular":[78,91],"margin":[79,92],"and":[80,95,110,130,139],"ACL":[83,106],"improves":[84,114],"by":[87],"explicitly":[88],"adding":[89],"an":[90],"between":[93],"positive":[94],"negative":[96],"augmented":[97],"pairs":[98],"SSL.":[100],"Experimental":[101],"results":[102],"show":[103],"using":[105,122,137],"both":[108],"supervised":[109,138],"unsupervised":[111],"significantly":[113],"performance.":[115],"We":[116],"validated":[117],"our":[118],"FSDnoisy18k":[124],"dataset,":[125],"where":[126],"achieved":[128],"73.6%":[129],"77.1%":[131],"accuracy":[132],"sound":[134],"event":[135],"classification":[136],"self-supervised":[140],"learning,":[141],"respectively.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}