{"id":"https://openalex.org/W2981512587","doi":"https://doi.org/10.1109/icassp40776.2020.9054619","title":"A Prototypical Triplet Loss for Cover Detection","display_name":"A Prototypical Triplet Loss for Cover Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981512587","doi":"https://doi.org/10.1109/icassp40776.2020.9054619","mag":"2981512587"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082487751","display_name":"Guillaume Doras","orcid":"https://orcid.org/0000-0002-8454-1968"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guillaume Doras","raw_affiliation_strings":["Sacem & Ircam Lab, CNRS, Sorbonne Universit\u00e9","CNRS, Sorbonne Universit\u00e9,Sacem & Ircam Lab"],"affiliations":[{"raw_affiliation_string":"Sacem & Ircam Lab, CNRS, Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CNRS, Sorbonne Universit\u00e9,Sacem & Ircam Lab","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082487751"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00697414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3797","last_page":"3801"},"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":0.9983999729156494,"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":0.9968000054359436,"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":0.8022019863128662},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6708406209945679},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6192508935928345},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.615465521812439},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5396547317504883},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4988703727722168},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48919132351875305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44335728883743286},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4421502351760864},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4212076961994171},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36146336793899536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022019863128662},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6708406209945679},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6192508935928345},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.615465521812439},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5396547317504883},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4988703727722168},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48919132351875305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44335728883743286},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4421502351760864},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4212076961994171},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36146336793899536},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.09862","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09862","pdf_url":"https://arxiv.org/pdf/1910.09862","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2981512587","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.09862","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:HAL:hal-04448257v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04448257","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, France. pp.3797-3801, ⟨10.1109/ICASSP40776.2020.9054619⟩","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1910.09862","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.09862","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},{"id":"doi:10.17023/kdhj-6314","is_oa":true,"landing_page_url":"https://doi.org/10.17023/kdhj-6314","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09862","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09862","pdf_url":"https://arxiv.org/pdf/1910.09862","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981512587.pdf","grobid_xml":"https://content.openalex.org/works/W2981512587.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W216397362","https://openalex.org/W1486009449","https://openalex.org/W1494374744","https://openalex.org/W1898424075","https://openalex.org/W1901129140","https://openalex.org/W1976069042","https://openalex.org/W2015563892","https://openalex.org/W2096733369","https://openalex.org/W2097461116","https://openalex.org/W2101722322","https://openalex.org/W2106053110","https://openalex.org/W2110644015","https://openalex.org/W2130556178","https://openalex.org/W2131739315","https://openalex.org/W2138452642","https://openalex.org/W2144935315","https://openalex.org/W2145902342","https://openalex.org/W2296610835","https://openalex.org/W2394827912","https://openalex.org/W2401823607","https://openalex.org/W2520774990","https://openalex.org/W2538860156","https://openalex.org/W2573162114","https://openalex.org/W2601450892","https://openalex.org/W2773294482","https://openalex.org/W2784180354","https://openalex.org/W2921083967","https://openalex.org/W2991402284","https://openalex.org/W3091905774","https://openalex.org/W3099206234","https://openalex.org/W6608682707","https://openalex.org/W6639352576","https://openalex.org/W6639824700","https://openalex.org/W6675751002","https://openalex.org/W6676956424","https://openalex.org/W6680962578","https://openalex.org/W6681300290","https://openalex.org/W6682527865","https://openalex.org/W6697451111","https://openalex.org/W6712631718","https://openalex.org/W6713057566","https://openalex.org/W6726946684","https://openalex.org/W6729231832","https://openalex.org/W6732288382","https://openalex.org/W6735236233","https://openalex.org/W6746836464","https://openalex.org/W6764992649","https://openalex.org/W6783596713","https://openalex.org/W7047274979"],"related_works":["https://openalex.org/W3015962533","https://openalex.org/W2991402284","https://openalex.org/W2183593396","https://openalex.org/W3015271757","https://openalex.org/W1788707484","https://openalex.org/W2896968054","https://openalex.org/W3120616375","https://openalex.org/W3033270690","https://openalex.org/W2997349786","https://openalex.org/W3099495704","https://openalex.org/W3029678209","https://openalex.org/W2921310091","https://openalex.org/W2182400267","https://openalex.org/W85425868","https://openalex.org/W3196959210","https://openalex.org/W3045171310","https://openalex.org/W2764078136","https://openalex.org/W3136659639","https://openalex.org/W2614884468"],"abstract_inverted_index":{"Automatic":[0],"cover":[1,80],"detection":[2],"--":[3,18],"the":[4,84,116],"task":[5],"of":[6,14],"finding":[7],"in":[8,26,83,94],"a":[9,15,22,32,55,63,139,171],"audio":[10,45],"dataset":[11,195],"all":[12],"covers":[13,107,179],"query":[16],"track":[17],"has":[19],"long":[20],"been":[21],"challenging":[23],"theoretical":[24],"problem":[25,61],"MIR":[27],"community.":[28],"It":[29],"also":[30],"became":[31],"practical":[33],"need":[34],"for":[35,90,189],"music":[36,121],"composers":[37],"societies":[38],"requiring":[39],"to":[40,51,72,78,150,177],"detect":[41],"automatically":[42],"if":[43],"an":[44,73],"excerpt":[46],"embeds":[47],"musical":[48],"content":[49],"belonging":[50],"their":[52],"catalog.":[53],"In":[54],"recent":[56],"work,":[57],"we":[58,159],"addressed":[59],"this":[60,98],"with":[62,100,126,163],"convolutional":[64],"neural":[65],"network":[66],"mapping":[67],"each":[68],"track's":[69],"dominant":[70,161],"melody":[71,162],"embedding":[74],"vector,":[75],"and":[76,146,169,197],"trained":[77],"minimize":[79],"pairs":[81],"distance":[82],"embeddings":[85],"space,":[86],"while":[87],"maximizing":[88],"it":[89],"non-covers.":[91],"We":[92,135,181],"showed":[93],"particular":[95],"that":[96,183],"training":[97],"model":[99],"enough":[101],"works":[102,125],"having":[103],"five":[104],"or":[105,128,132],"more":[106],"yields":[108],"state-of-the-art":[109],"results.":[110],"This":[111],"however":[112],"does":[113],"not":[114],"reflect":[115],"realistic":[117],"use":[118,192],"case,":[119],"where":[120],"catalogs":[122],"typically":[123],"contain":[124],"zero":[127],"at":[129],"most":[130],"one":[131],"two":[133,148,190],"covers.":[134],"thus":[136],"introduce":[137],"here":[138],"new":[140],"test":[141],"set":[142],"incorporating":[143],"these":[144,156,184],"constraints,":[145],"propose":[147],"contributions":[149],"improve":[151,178,186],"our":[152],"model's":[153],"accuracy":[154],"under":[155],"stricter":[157],"conditions:":[158],"replace":[160],"multi-pitch":[164],"representation":[165],"as":[166],"input":[167],"data,":[168],"describe":[170],"novel":[172],"prototypical":[173],"triplet":[174],"loss":[175],"designed":[176],"clustering.":[180],"show":[182],"changes":[185],"results":[187],"significantly":[188],"concrete":[191],"cases,":[193],"large":[194],"lookup":[196],"live":[198],"songs":[199],"identification.":[200]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}