{"id":"https://openalex.org/W6910350114","doi":"https://doi.org/10.48550/arxiv.2208.09646","title":"An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio","display_name":"An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio","publication_year":2022,"publication_date":"2022-08-20","ids":{"openalex":"https://openalex.org/W6910350114","doi":"https://doi.org/10.48550/arxiv.2208.09646"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2208.09646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.09646","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2208.09646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yan, Xinrui","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan, Xinrui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yi, Jiangyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Jiangyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tao, Jianhua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Jianhua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Chenglong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenglong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ma, Haoxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Haoxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Shiming","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shiming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fu, Ruibo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Ruibo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":true,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.46149998903274536,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.46149998903274536,"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/T11309","display_name":"Music and Audio Processing","score":0.2709999978542328,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.019899999722838402,"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/visualization","display_name":"Visualization","score":0.557200014591217},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33959999680519104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3391999900341034},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.30469998717308044},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3041999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979000210762024},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5054000020027161},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.30469998717308044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.30300000309944153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2208.09646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.09646","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2208.09646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.09646","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5875627994537354,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"effective":[1],"attempts":[2],"have":[3,65],"been":[4],"made":[5],"for":[6,46],"fake":[7,35,51],"audio":[8,36],"detection.":[9],"However,":[10],"they":[11],"can":[12],"only":[13],"provide":[14],"detection":[15],"results":[16],"but":[17],"no":[18],"countermeasures":[19],"to":[20],"curb":[21],"this":[22],"harm.":[23],"For":[24],"many":[25],"related":[26],"practical":[27],"applications,":[28],"what":[29],"model":[30,71],"or":[31],"algorithm":[32],"generated":[33],"the":[34,57,68],"also":[37],"is":[38],"needed.":[39],"Therefore,":[40],"We":[41,64],"propose":[42],"a":[43],"new":[44],"problem":[45],"detecting":[47],"vocoder":[48,82],"fingerprints":[49],"of":[50],"audio.":[52],"Experiments":[53],"are":[54],"conducted":[55],"on":[56],"datasets":[58],"synthesized":[59],"by":[60],"eight":[61],"state-of-the-art":[62],"vocoders.":[63],"preliminarily":[66],"explored":[67],"features":[69],"and":[70],"architectures.":[72],"The":[73],"t-SNE":[74],"visualization":[75],"shows":[76],"that":[77],"different":[78],"vocoders":[79],"generate":[80],"distinct":[81],"fingerprints.":[83]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}