{"id":"https://openalex.org/W4403792468","doi":"https://doi.org/10.1145/3664647.3681602","title":"Utilizing Speaker Profiles for Impersonation Audio Detection","display_name":"Utilizing Speaker Profiles for Impersonation Audio Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792468","doi":"https://doi.org/10.1145/3664647.3681602"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681602","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681602","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101361643","display_name":"Hao Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Gu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004011841","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0002-5785-7027"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109525927","display_name":"Yong Ren","orcid":"https://orcid.org/0009-0000-9015-000X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026806223","display_name":"Xinrui Yan","orcid":"https://orcid.org/0000-0002-6499-0272"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrui Yan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459047","display_name":"Yujie Chen","orcid":"https://orcid.org/0000-0003-2513-7559"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Chen","raw_affiliation_strings":["Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080169535","display_name":"Xiaohui Zhang","orcid":"https://orcid.org/0000-0002-9949-5415"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101361643"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.7009,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69924134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1961","last_page":"1970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7956045866012573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4344896674156189}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956045866012573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4344896674156189}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681602","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681602","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2047346462","https://openalex.org/W2123299109","https://openalex.org/W2141074280","https://openalex.org/W2146320039","https://openalex.org/W2194775991","https://openalex.org/W2963460857","https://openalex.org/W2982058372","https://openalex.org/W2989571531","https://openalex.org/W2997686727","https://openalex.org/W3026777299","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3160614129","https://openalex.org/W3163596559","https://openalex.org/W3201773091","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221138880","https://openalex.org/W4313547876","https://openalex.org/W4366456842","https://openalex.org/W4378446151","https://openalex.org/W4386302282"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Fake":[0],"audio":[1,83,102,177,184],"detection":[2,80,185],"is":[3,39,138],"an":[4,35,45],"emerging":[5],"active":[6],"topic.":[7],"A":[8],"growing":[9],"number":[10],"of":[11,53,81,100,148],"literatures":[12],"have":[13],"aimed":[14],"to":[15,114,124,128,170],"detect":[16],"fake":[17,41,183],"utterance,":[18],"which":[19,61],"are":[20,106,110],"mostly":[21],"generated":[22],"by":[23],"Text-to-speech":[24],"(TTS)":[25],"or":[26,66],"voice":[27],"conversion":[28],"(VC).":[29],"However,":[30],"countermeasures":[31],"against":[32],"impersonation":[33,69,82,101,134,149,163,176,214],"remain":[34],"underexplored":[36],"area.":[37],"Impersonation":[38],"a":[40,54,84,90],"type":[42],"that":[43,93,109,202],"involves":[44,70],"imitator":[46],"replicating":[47],"specific":[48],"traits":[49],"and":[50,59,195],"speech":[51,142],"style":[52],"target":[55],"speaker.":[56],"Unlike":[57],"TTS":[58],"VC,":[60],"often":[62],"leave":[63],"digital":[64],"traces":[65],"signal":[67],"artifacts,":[68],"live":[71],"human":[72],"beings":[73],"producing":[74],"entirely":[75],"natural":[76],"speech,":[77],"rendering":[78],"the":[79,98,158,172,196,209],"challenging":[85,111],"task.":[86],"Thus,":[87],"we":[88,155],"propose":[89],"novel":[91],"method":[92],"integrates":[94],"speaker":[95,204],"profiles":[96,105,205],"into":[97],"process":[99],"detection.":[103,178],"Speaker":[104],"inherent":[107],"characteristics":[108],"for":[112,132,145],"impersonators":[113],"mimic":[115],"accurately,":[116],"such":[117],"as":[118],"speaker's":[119],"age,":[120],"job.":[121],"We":[122,179],"aim":[123],"leverage":[125],"these":[126],"features":[127],"extract":[129],"discriminative":[130],"information":[131],"detecting":[133,213],"audio.":[135,215],"Moreover,":[136],"there":[137],"no":[139],"large":[140],"impersonated":[141],"corpora":[143],"available":[144],"quantitative":[146],"study":[147],"impacts.":[150],"To":[151],"address":[152],"this":[153],"gap,":[154],"further":[156],"design":[157],"first":[159],"large-scale,":[160],"diverse-speaker":[161],"Chinese":[162],"dataset,":[164],"named":[165],"ImPersonation":[166],"Audio":[167],"Detection":[168],"(IPAD),":[169],"advance":[171],"community's":[173],"research":[174],"on":[175,187],"evaluate":[180],"several":[181],"existing":[182],"methods":[186],"our":[188,199],"proposed":[189],"dataset":[190],"IPAD,":[191],"demonstrating":[192],"its":[193],"necessity":[194],"challenges.":[197],"Additionally,":[198],"findings":[200],"reveal":[201],"incorporating":[203],"can":[206],"significantly":[207],"enhance":[208],"model's":[210],"performance":[211],"in":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}