{"id":"https://openalex.org/W7108611688","doi":"https://doi.org/10.5281/zenodo.17811423","title":"Refining music sample identification with a self-supervised graph neural network","display_name":"Refining music sample identification with a self-supervised graph neural network","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108611688","doi":"https://doi.org/10.5281/zenodo.17811423"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811423","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811423","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811423","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aditya Bhattacharjee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aditya Bhattacharjee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ivan Meresman Higgs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Meresman Higgs","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mark Sandler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Sandler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Emmanouil Benetos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62161356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.9944999814033508,"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/T13996","display_name":"Diverse Musicological Studies","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.00039999998989515007,"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/scalability","display_name":"Scalability","score":0.5562000274658203},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5447999835014343},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5322999954223633},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4196000099182129},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4154999852180481},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.38350000977516174},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35589998960494995},{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.3463999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058000206947327},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5447999835014343},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27709999680519104},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811423","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811423","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811423","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811423","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"sample":[1],"identification":[2,8],"(ASID)":[3],"-":[4,22,176],"the":[5,30,120,125,171,208],"detection":[6],"and":[7,83,100,169],"of":[9,11,32,119,139,151,173,216],"portions":[10],"audio":[12,33,40],"recordings":[13],"that":[14,63,165],"have":[15,64],"been":[16],"reused":[17],"in":[18,29,46,181,188,194],"new":[19,204],"musical":[20,49,66],"works":[21],"is":[23,88],"an":[24,89,152,177],"essential":[25,178],"but":[26],"challenging":[27],"task":[28],"field":[31],"query-based":[34],"retrieval.":[35],"While":[36],"a":[37,69,98,105,110,134,147,162],"related":[38],"task,":[39],"fingerprinting,":[41],"has":[42],"made":[43],"significant":[44],"progress":[45],"accurately":[47],"retrieving":[48],"content":[50],"under":[51],"\"real":[52],"world\"":[53],"(noisy,":[54],"reverberant)":[55],"conditions,":[56],"ASID":[57],"systems":[58],"struggle":[59],"to":[60,72,124],"identify":[61],"samples":[62],"undergone":[65],"modifications.":[67],"Thus,":[68],"system":[70,128,199],"robust":[71],"common":[73],"music":[74,87],"production":[75],"transformations":[76],"such":[77],"as":[78,186,214],"time-stretching,":[79],"pitch-shifting,":[80],"effects":[81],"processing,":[82],"underlying":[84],"or":[85],"overlaying":[86],"important":[90],"open":[91],"challenge.":[92],"In":[93,184],"this":[94,217],"work,":[95],"we":[96,145,196,212],"propose":[97],"lightweight":[99],"scalable":[101],"encoding":[102],"architecture":[103],"employing":[104],"Graph":[106],"Neural":[107],"Network":[108],"within":[109],"contrastive":[111],"learning":[112],"framework.":[113],"Our":[114],"model":[115],"uses":[116],"only":[117],"9%":[118],"trainable":[121],"parameters":[122],"compared":[123],"current":[126],"state-of-the-art":[127],"while":[129],"achieving":[130],"comparable":[131],"performance,":[132],"reaching":[133],"mean":[135],"average":[136],"precision":[137],"(mAP)":[138],"44.2%.":[140],"To":[141],"enhance":[142],"retrieval":[143],"quality,":[144],"introduce":[146],"two-stage":[148],"approach":[149],"consisting":[150],"initial":[153],"coarse":[154],"similarity":[155],"search":[156],"for":[157,200,207],"candidate":[158],"selection,":[159],"followed":[160],"by":[161],"cross-attention":[163],"classifier":[164],"rejects":[166],"irrelevant":[167],"matches":[168],"refines":[170],"ranking":[172],"retrieved":[174],"candidates":[175],"capability":[179],"absent":[180],"prior":[182],"models.":[183],"addition,":[185],"queries":[187,202],"real-world":[189],"applications":[190],"are":[191],"often":[192],"short":[193,201],"duration,":[195],"benchmark":[197],"our":[198],"using":[203],"fine-grained":[205],"annotations":[206],"Sample100":[209],"dataset,":[210],"which":[211],"publish":[213],"part":[215],"work.":[218]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}