{"id":"https://openalex.org/W4387543539","doi":"https://doi.org/10.1145/3616195.3616215","title":"Supervised Contrastive Learning For Musical Onset Detection","display_name":"Supervised Contrastive Learning For Musical Onset Detection","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387543539","doi":"https://doi.org/10.1145/3616195.3616215"},"language":"en","primary_location":{"id":"doi:10.1145/3616195.3616215","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3616195.3616215","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001299911","display_name":"J.H. Bolt","orcid":"https://orcid.org/0009-0005-8093-849X"},"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":"James Bolt","raw_affiliation_strings":["Queen Mary University of London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-8093-849X","affiliations":[{"raw_affiliation_string":"Queen Mary University of 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":"Gy\u00f6Rgy Fazekas","raw_affiliation_strings":["Queen Mary University of London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2580-0007","affiliations":[{"raw_affiliation_string":"Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001299911"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.5757,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65218199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"135"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9927999973297119,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7013332843780518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980360746383667},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.6795692443847656},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49151453375816345},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4846802055835724},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.475288987159729},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45294708013534546},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.41954344511032104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37902167439460754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35185831785202026},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33548882603645325}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7013332843780518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980360746383667},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.6795692443847656},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49151453375816345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4846802055835724},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.475288987159729},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45294708013534546},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.41954344511032104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37902167439460754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35185831785202026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33548882603645325},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3616195.3616215","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3616195.3616215","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3616195.3616215","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3616195.3616215","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387543539.pdf","grobid_xml":"https://content.openalex.org/works/W4387543539.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2036339641","https://openalex.org/W2096733369","https://openalex.org/W2809254203","https://openalex.org/W2964051853","https://openalex.org/W3162391496","https://openalex.org/W4220931296","https://openalex.org/W4301953474","https://openalex.org/W4376577227"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2770593030","https://openalex.org/W4321487865","https://openalex.org/W3154990682","https://openalex.org/W4313906399","https://openalex.org/W2560201613","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W4385386361","https://openalex.org/W2994927414"],"abstract_inverted_index":{"This":[0,49,79,89,142],"paper":[1],"applies":[2],"supervised":[3,70,92,147,158],"contrastive":[4,71,93,118,148,159],"learning":[5,149],"to":[6,10,57,82,97,171],"musical":[7],"onset":[8,19,98,154,165],"detection":[9,99,166],"alleviate":[11],"the":[12,59,66,69,83,114,117,122,138,144,174],"issue":[13],"of":[14,42,47,77,87,135,146],"noisy":[15],"annotated":[16,45],"data":[17,50,61,68,152,175],"for":[18,137,153],"datasets.":[20,37],"The":[21,38],"results":[22],"are":[23],"compared":[24],"against":[25],"a":[26,43,130,163],"state-of-the-art,":[27],"convolutional,":[28],"cross-entropy":[29,84,104,123],"model.":[30],"Both":[31],"models":[32,105],"were":[33],"trained":[34,64,112],"on":[35,65,113],"two":[36],"first":[39],"dataset":[40],"comprised":[41],"manually":[44],"selection":[46],"music.":[48],"was":[51,80],"then":[52],"augmented":[53,115],"with":[54,129,150],"inaccurate":[55,140,151],"labelling":[56],"produce":[58],"second":[60],"set.":[62],"When":[63,111],"original":[67],"model":[72,85,119,124],"produced":[73],"an":[74,107],"F1":[75,133],"score":[76,86,134],"0.878.":[78],"close":[81],"0.888.":[88],"showed":[90],"that":[91,157],"loss":[94,160],"is":[95,169],"applicable":[96],"but":[100],"does":[101],"not":[102],"outperform":[103],"in":[106,132,173,178],"ideal":[108],"training":[109],"case.":[110],"set":[116],"consistently":[120],"outperformed":[121],"across":[125],"increasing":[126],"percentage":[127],"inaccuracies,":[128],"difference":[131],"0.1":[136],"most":[139],"data.":[141],"demonstrates":[143],"robustness":[145],"detection,":[155],"suggesting":[156],"could":[161],"provide":[162],"new":[164],"architecture":[167],"which":[168],"invariant":[170],"noise":[172],"or":[176],"inaccuracies":[177],"labelling.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}