{"id":"https://openalex.org/W7108653188","doi":"https://doi.org/10.5281/zenodo.17811353","title":"PeakNetFP: Peak-based Neural Audio Fingerprinting Robust to Extreme Time Stretching","display_name":"PeakNetFP: Peak-based Neural Audio Fingerprinting Robust to Extreme Time Stretching","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108653188","doi":"https://doi.org/10.5281/zenodo.17811353"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811353","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811353","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.17811353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":"Benjamin Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Martin","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":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Romain Hennequin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Hennequin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.54726418,"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":0.9742000102996826,"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":0.9742000102996826,"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":0.009100000374019146,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/leverage","display_name":"Leverage (statistics)","score":0.6367999911308289},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5525000095367432},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5356000065803528},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5216000080108643},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.484499990940094},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4756999909877777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403999924659729},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6367999911308289},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811353","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811353","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.17811353","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811353","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,16,62],"work":[1],"introduces":[2],"PeakNetFP,":[3],"the":[4,23,43,56,158,165,176,185],"first":[5],"neural":[6,172],"audio":[7,82],"fingerprinting":[8],"(AFP)":[9],"system":[10,18,145],"designed":[11,20],"specifically":[12],"around":[13],"spectral":[14,25],"peaks.":[15],"novel":[17],"is":[19,49,141],"to":[21,42,66,75,102,111],"leverage":[22],"sparse":[24],"coordinates":[26],"typically":[27],"computed":[28],"by":[29],"traditional":[30],"peak-based":[31,162],"AFP":[32,69,136,152,163],"methods.":[33],"PeakNetFP":[34,65,87,105,129],"performs":[35],"hierarchical":[36],"point":[37],"feature":[38],"extraction":[39],"techniques":[40],"similar":[41],"computer":[44],"vision":[45],"model":[46],"PointNet++,":[47],"and":[48,71,119,132,167,181],"trained":[50],"using":[51],"contrastive":[52],"learning":[53,59],"like":[54],"in":[55,184],"state-of-the-art":[57],"deep":[58],"AFP,":[60],"NeuralFP.":[61],"combination":[63],"allows":[64],"outperform":[67],"conventional":[68],"systems":[70],"achieves":[72],"comparable":[73],"performance":[74],"NeuralFP":[76],"when":[77],"handling":[78],"challenging":[79],"time":[80,139],"stretched":[81],"data.":[83,125],"In":[84],"extensive":[85],"evaluation,":[86],"maintains":[88],"a":[89,130,147],"Top-1":[90],"hit":[91],"rate":[92],"of":[93,161,171],"over":[94],"90%":[95],"for":[96,135,150,178],"stretching":[97,140],"factors":[98],"ranging":[99],"from":[100],"50%":[101],"200%.":[103],"Moreover,":[104],"offers":[106],"significant":[107],"efficiency":[108],"advantages:":[109],"compared":[110],"NeuralFP,":[112],"it":[113,155],"has":[114],"100":[115],"times":[116,122],"fewer":[117],"parameters":[118],"uses":[120],"11":[121],"smaller":[123],"input":[124],"These":[126],"features":[127],"make":[128],"lightweight":[131,159],"efficient":[133,182],"solution":[134],"tasks":[137],"where":[138],"involved.":[142],"Overall,":[143],"this":[144],"represents":[146],"promising":[148],"direction":[149],"future":[151],"technologies,":[153],"as":[154],"successfully":[156],"merges":[157],"nature":[160],"with":[164],"adaptability":[166],"pattern":[168],"recognition":[169],"capabilities":[170],"network-based":[173],"approaches,":[174],"paving":[175],"way":[177],"more":[179],"scalable":[180],"solutions":[183],"field.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-05T00:00:00"}