{"id":"https://openalex.org/W7140464591","doi":"https://doi.org/10.48550/arxiv.2603.23947","title":"Variable-Length Audio Fingerprinting","display_name":"Variable-Length Audio Fingerprinting","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140464591","doi":"https://doi.org/10.48550/arxiv.2603.23947"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.23947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.23947","pdf_url":"https://arxiv.org/pdf/2603.23947","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.23947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130687475","display_name":"Hongjie Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130651192","display_name":"Hanyu Meng","orcid":"https://orcid.org/0009-0004-6123-0587","observed_orcids":["https://orcid.org/0009-0004-6123-0587"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Hanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094579707","display_name":"Huimin Zeng","orcid":"https://orcid.org/0000-0003-0198-2352","observed_orcids":["https://orcid.org/0000-0003-0198-2352"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Huimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009957887","display_name":"Ryan A. Rossi","orcid":"https://orcid.org/0000-0001-9758-0635","observed_orcids":["https://orcid.org/0000-0001-9758-0635"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossi, Ryan A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130647941","display_name":"Lie Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Lie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055864113","display_name":"Josh Kimball","orcid":"https://orcid.org/0009-0009-9586-2044","observed_orcids":["https://orcid.org/0009-0009-9586-2044"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kimball, Josh","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-fingerprinting","display_name":"audio fingerprinting","score":0.9890000224113464},{"id":"https://openalex.org/keywords/audio-identification","display_name":"audio identification","score":0.5569999814033508},{"id":"https://openalex.org/keywords/audio-retrieval","display_name":"audio retrieval","score":0.9490000009536743},{"id":"https://openalex.org/keywords/temporal-dynamics","display_name":"temporal dynamics","score":0.7310000061988831},{"id":"https://openalex.org/keywords/audio-segmentation","display_name":"audio segmentation","score":0.8730000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.7311999797821045},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5794000029563904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5756999850273132},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302000045776367},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5171999931335449},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4415000081062317},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.4004000127315521},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3935999870300293},{"id":"https://openalex.org/C168406668","wikidata":"https://www.wikidata.org/wiki/Q178022","display_name":"Fingerprint recognition","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.23947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.23947","pdf_url":"https://arxiv.org/pdf/2603.23947","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.23947","doi":"https://doi.org/10.48550/arxiv.2603.23947","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23947","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.23947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.23947","pdf_url":"https://arxiv.org/pdf/2603.23947","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415182357","https://openalex.org/W7125788889","https://openalex.org/W3093814547","https://openalex.org/W2102169259","https://openalex.org/W3017057111","https://openalex.org/W4402112609","https://openalex.org/W3083949434","https://openalex.org/W3162472933","https://openalex.org/W7168041033","https://openalex.org/W166806076"],"abstract_inverted_index":{"Audio":[0,46],"fingerprinting":[1,68],"converts":[2],"audio":[3,28,67,73,92,95],"to":[4,11,40],"much":[5],"lower-dimensional":[6],"representations,":[7],"allowing":[8],"distorted":[9],"recordings":[10],"still":[12],"be":[13],"recognized":[14],"as":[15],"their":[16],"originals":[17],"through":[18],"similar":[19],"fingerprints.":[20],"Existing":[21],"deep":[22,66],"learning":[23],"approaches":[24],"rigidly":[25],"fingerprint":[26],"fixed-length":[27],"segments,":[29],"thereby":[30],"neglecting":[31],"temporal":[32],"dynamics":[33],"during":[34],"segmentation.":[35],"To":[36,56],"address":[37],"limitations":[38],"due":[39],"this":[41],"rigidity,":[42],"we":[43],"propose":[44],"Variable-Length":[45],"FingerPrinting":[47],"(VLAFP),":[48],"a":[49],"novel":[50],"method":[51],"that":[52,85],"supports":[53],"variable-length":[54],"fingerprinting.":[55],"the":[57,64],"best":[58],"of":[59,71,74],"our":[60],"knowledge,":[61],"VLAFP":[62,86],"is":[63],"first":[65],"model":[69],"capable":[70],"processing":[72],"variable":[75],"length,":[76],"for":[77],"both":[78],"training":[79],"and":[80,94],"testing.":[81],"Our":[82],"experiments":[83],"show":[84],"outperforms":[87],"existing":[88],"state-of-the-arts":[89],"in":[90],"live":[91],"identification":[93],"retrieval":[96],"across":[97],"three":[98],"real-world":[99],"datasets.":[100]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-27T00:00:00"}