{"id":"https://openalex.org/W7108676582","doi":"https://doi.org/10.5281/zenodo.17811394","title":"Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification","display_name":"Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108676582","doi":"https://doi.org/10.5281/zenodo.17811394"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811394","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811394","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Recep Oguz Araz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Recep Oguz Araz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guillem Cort\u00e8s-Sebasti\u00e0","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillem Cort\u00e8s-Sebasti\u00e0","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Emilio Molina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emilio Molina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Joan Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joan Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhki Mitsufuji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhki Mitsufuji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Dmitry Bogdanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Bogdanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.53952466,"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":0.7724999785423279,"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":0.7724999785423279,"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":0.15330000221729279,"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":0.01860000006854534,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6420000195503235},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5306000113487244},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4627000093460083},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.460999995470047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4307999908924103},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4066999852657318},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702000141143799},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6420000195503235},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5378999710083008},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049999952316284},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4627000093460083},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3147999942302704},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C168406668","wikidata":"https://www.wikidata.org/wiki/Q178022","display_name":"Fingerprint recognition","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811394","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811394","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811394","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811394","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":"ConferencePaper"},"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":{"Audio":[0],"fingerprinting":[1],"(AFP)":[2],"allows":[3],"the":[4,40,43,46,81,86,117,127,137],"identification":[5],"of":[6,42,99,121,129,136],"unknown":[7],"audio":[8,15,25,56],"content":[9],"by":[10,39,105],"extracting":[11],"compact":[12],"representations,":[13],"termed":[14,163],"fingerprints,":[16],"that":[17,132,147],"are":[18],"designed":[19],"to":[20,78,102],"remain":[21],"robust":[22],"against":[23],"common":[24],"degradations.":[26],"Neural":[27],"AFP":[28,75],"methods":[29,76],"often":[30],"employ":[31],"metric":[32,67,123],"learning,":[33],"where":[34],"representation":[35],"quality":[36],"is":[37,165],"influenced":[38],"nature":[41],"supervision":[44],"and":[45,110,170,181],"utilized":[47],"loss":[48,83,139,159],"function.":[49],"However,":[50],"recent":[51,87],"work":[52],"unrealistically":[53],"simulates":[54],"real-life":[55],"degradation":[57],"during":[58],"training,":[59],"yielding":[60],"sub-optimal":[61],"supervision.":[62],"Additionally,":[63],"although":[64],"several":[65],"modern":[66],"learning":[68,124],"approaches":[69,125],"have":[70],"been":[71],"proposed,":[72],"current":[73],"neural":[74],"continue":[77],"rely":[79],"on":[80,174],"NT\u2011Xent":[82],"without":[84],"exploring":[85],"advances":[88],"or":[89],"classical":[90],"alternatives.":[91],"In":[92],"this":[93],"work,":[94],"we":[95],"propose":[96],"a":[97,133,176],"series":[98],"best":[100],"practices":[101],"enhance":[103],"self-supervision":[104],"leveraging":[106],"musical":[107],"signal":[108],"properties":[109],"realistic":[111],"room":[112],"acoustics.":[113],"We":[114],"then":[115],"present":[116],"first":[118],"systematic":[119],"evaluation":[120],"various":[122],"in":[126,189],"context":[128],"AFP,":[130],"demonstrating":[131],"self\u2011supervised":[134],"adaptation":[135],"triplet":[138],"yields":[140],"superior":[141],"performance.":[142],"Our":[143,161],"results":[144],"also":[145],"reveal":[146],"training":[148],"with":[149],"multiple":[150],"positives":[151],"per":[152],"anchor":[153],"has":[154],"critically":[155],"different":[156],"effects":[157],"across":[158],"functions.":[160],"approach,":[162],"NMFP,":[164],"built":[166],"upon":[167],"these":[168],"insights":[169],"achieves":[171],"state-of-the-art":[172],"performance":[173],"both":[175],"large,":[177],"synthetically":[178],"degraded":[179],"dataset":[180,184],"an":[182],"industrial":[183],"recorded":[185],"using":[186],"real":[187],"microphones":[188],"diverse":[190],"music":[191],"venues.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}