{"id":"https://openalex.org/W4372266854","doi":"https://doi.org/10.1109/icassp49357.2023.10095292","title":"Tempo vs. Pitch: Understanding Self-Supervised Tempo Estimation","display_name":"Tempo vs. Pitch: Understanding Self-Supervised Tempo Estimation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266854","doi":"https://doi.org/10.1109/icassp49357.2023.10095292"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095292","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/A5090343957","display_name":"Giovana Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Giovana Morais","raw_affiliation_strings":["University of São Paulo,Computer Science Dept.,São Paulo,Brazil"],"affiliations":[{"raw_affiliation_string":"University of São Paulo,Computer Science Dept.,São Paulo,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033390365","display_name":"Matthew E. P. Davies","orcid":"https://orcid.org/0000-0002-1315-3992"},"institutions":[{"id":"https://openalex.org/I4210093196","display_name":"Sirius University of Science and Technology","ror":"https://ror.org/00n51jg89","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210093196"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Matthew E. P. Davies","raw_affiliation_strings":["SiriusXM,USA","SiriusXM, USA"],"affiliations":[{"raw_affiliation_string":"SiriusXM,USA","institution_ids":["https://openalex.org/I4210093196"]},{"raw_affiliation_string":"SiriusXM, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049168435","display_name":"Marcelo Cavalheiro de Queiroz","orcid":"https://orcid.org/0000-0003-2347-0921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcelo Queiroz","raw_affiliation_strings":["University of São Paulo,Computer Science Dept.,São Paulo,Brazil"],"affiliations":[{"raw_affiliation_string":"University of São Paulo,Computer Science Dept.,São Paulo,Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,MARL-IDM,New York,USA","MARL-IDM, New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University,MARL-IDM,New York,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"MARL-IDM, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090343957"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2405,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78772888,"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":"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":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":0.9930999875068665,"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/T10860","display_name":"Speech and Audio Processing","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561972141265869},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6591238379478455},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5626057982444763},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5395104289054871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4943044185638428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4832242429256439},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.43542227149009705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42990636825561523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561972141265869},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6591238379478455},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5626057982444763},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5395104289054871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943044185638428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4832242429256439},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.43542227149009705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42990636825561523},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095292","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":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W4650756","https://openalex.org/W1522301498","https://openalex.org/W2031396843","https://openalex.org/W2096623359","https://openalex.org/W2133824856","https://openalex.org/W2135563421","https://openalex.org/W2191779130","https://openalex.org/W2478051194","https://openalex.org/W2538924665","https://openalex.org/W2901314291","https://openalex.org/W2903493144","https://openalex.org/W3003199504","https://openalex.org/W3003257820","https://openalex.org/W3011176162","https://openalex.org/W3081288434","https://openalex.org/W3118825798","https://openalex.org/W3172444685","https://openalex.org/W3185614832","https://openalex.org/W4280498166","https://openalex.org/W4297631129","https://openalex.org/W6600180983","https://openalex.org/W6631190155","https://openalex.org/W6680219554","https://openalex.org/W6756419834","https://openalex.org/W6756801033","https://openalex.org/W6773406229","https://openalex.org/W6796928388","https://openalex.org/W6838236130","https://openalex.org/W6843552097"],"related_works":["https://openalex.org/W161456234","https://openalex.org/W3123043866","https://openalex.org/W2765162471","https://openalex.org/W2367130511","https://openalex.org/W4235007455","https://openalex.org/W2354300066","https://openalex.org/W2996988663","https://openalex.org/W2276802262","https://openalex.org/W2089741817","https://openalex.org/W2358993285"],"abstract_inverted_index":{"Self-supervision":[0],"methods":[1,21],"learn":[2],"representations":[3],"by":[4,78],"solving":[5],"pretext":[6],"tasks":[7],"that":[8],"do":[9],"not":[10],"require":[11],"human-generated":[12],"labels,":[13],"alleviating":[14],"the":[15,46,55,99,102],"need":[16],"for":[17,41,83,87,108],"time-consuming":[18],"annotations.":[19],"These":[20],"have":[22],"been":[23],"applied":[24],"in":[25,36,45],"computer":[26],"vision,":[27],"natural":[28],"language":[29],"processing,":[30],"environmental":[31],"sound":[32],"analysis,":[33],"and":[34,65,105],"recently":[35],"music":[37],"information":[38],"retrieval,":[39],"e.g.":[40],"pitch":[42,84],"estimation.":[43,111],"Particularly":[44],"context":[47],"of":[48,57,63],"music,":[49],"there":[50],"are":[51],"few":[52],"insights":[53],"about":[54],"fragility":[56],"these":[58,76],"models":[59],"regarding":[60],"different":[61],"distributions":[62],"data,":[64],"how":[66],"they":[67],"could":[68],"be":[69],"mitigated.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,97],"explore":[75],"questions":[77],"dissecting":[79],"a":[80],"self-supervised":[81,109],"model":[82],"estimation":[85,89],"adapted":[86],"tempo":[88,110],"via":[90],"rigorous":[91],"experimentation":[92],"with":[93],"synthetic":[94],"data.":[95],"Specifically,":[96],"study":[98],"relationship":[100],"between":[101],"input":[103],"representation":[104],"data":[106],"distribution":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}