{"id":"https://openalex.org/W4298633870","doi":"https://doi.org/10.1145/3552466.3556532","title":"Improving Spoofing Capability for End-to-end Any-to-many Voice Conversion","display_name":"Improving Spoofing Capability for End-to-end Any-to-many Voice Conversion","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4298633870","doi":"https://doi.org/10.1145/3552466.3556532"},"language":"en","primary_location":{"id":"doi:10.1145/3552466.3556532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556532","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556532","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103185155","display_name":"Hua Hua","orcid":"https://orcid.org/0000-0003-4942-5395"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hua Hua","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368259","display_name":"Ziyi Chen","orcid":"https://orcid.org/0000-0001-6512-2824"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Chen","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443158","display_name":"Yuxiang Zhang","orcid":"https://orcid.org/0000-0003-4624-5663"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University, Suzhou, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103185155"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5613,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71139649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9995999932289124,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8491714000701904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037115335464478},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7992581725120544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6776244640350342},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5547894239425659},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.507668137550354},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5018913745880127},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.45548975467681885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32973963022232056},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2584822475910187},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16454899311065674}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8491714000701904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037115335464478},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7992581725120544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6776244640350342},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5547894239425659},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.507668137550354},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5018913745880127},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.45548975467681885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32973963022232056},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2584822475910187},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16454899311065674},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552466.3556532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556532","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3552466.3556532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556532","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298633870.pdf","grobid_xml":"https://content.openalex.org/works/W4298633870.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2402156731","https://openalex.org/W2590129515","https://openalex.org/W2593414223","https://openalex.org/W2745896134","https://openalex.org/W2902070858","https://openalex.org/W2913954081","https://openalex.org/W2936802426","https://openalex.org/W2938583109","https://openalex.org/W2938836228","https://openalex.org/W2963539064","https://openalex.org/W2964052309","https://openalex.org/W2964243274","https://openalex.org/W2967606780","https://openalex.org/W2972313557","https://openalex.org/W2972811785","https://openalex.org/W3016138785","https://openalex.org/W3026874504","https://openalex.org/W3096524539","https://openalex.org/W3098557217","https://openalex.org/W3110588169","https://openalex.org/W3162366763","https://openalex.org/W3197478142","https://openalex.org/W3198329097","https://openalex.org/W3198486673","https://openalex.org/W3199161700","https://openalex.org/W3203407300","https://openalex.org/W3209050974","https://openalex.org/W4221138880","https://openalex.org/W4300282602"],"related_works":["https://openalex.org/W4294437891","https://openalex.org/W4226389478","https://openalex.org/W2790784932","https://openalex.org/W4297792928","https://openalex.org/W3113108043","https://openalex.org/W4221161333","https://openalex.org/W2061278248","https://openalex.org/W4298202768","https://openalex.org/W1914543332","https://openalex.org/W2946856121"],"abstract_inverted_index":{"Audio":[0],"deep":[1],"synthesis":[2],"techniques":[3],"have":[4,23],"been":[5,24],"able":[6],"to":[7,17,26,36,54],"generate":[8],"high-quality":[9],"speech":[10,32],"whose":[11],"authenticity":[12],"is":[13],"difficult":[14],"for":[15],"humans":[16],"recognize.":[18],"Meanwhile,":[19],"many":[20],"anti-spoofing":[21,62,111],"systems":[22],"developed":[25],"capture":[27],"artifacts":[28],"in":[29,48,107,122],"the":[30,57,79,99],"synthesized":[31],"that":[33,98],"are":[34,118],"imperceptible":[35],"human":[37],"hearing,":[38],"thus":[39],"a":[40,66,75],"continuous":[41],"escalating":[42],"race":[43],"of":[44,59,81],"'attacking":[45],"and":[46,91,115],"defending'":[47],"voice":[49,70],"deepfake":[50],"has":[51],"started.":[52],"Hence,":[53],"further":[55],"improve":[56],"probability":[58],"successfully":[60],"cheating":[61],"systems,":[63],"we":[64],"propose":[65],"fully":[67],"end-to-end,":[68],"any-to-many":[69],"conversion":[71],"method":[72,101,125],"based":[73],"on":[74],"non-autoregressive":[76],"structure":[77],"with":[78],"addition":[80],"two":[82],"light":[83],"but":[84],"strong":[85],"post-processing":[86],"strategies":[87],"namely":[88],"silence":[89],"replacement":[90],"global":[92],"noise":[93],"perturbation.":[94],"Experimental":[95],"results":[96],"show":[97],"proposed":[100,124],"performs":[102],"better":[103],"than":[104],"current":[105],"baselines":[106],"fooling":[108],"several":[109],"state-of-the-art":[110],"systems.":[112],"Better":[113],"naturalness":[114],"speaker":[116],"similarity":[117],"also":[119],"achieved,":[120],"resulting":[121],"our":[123],"showing":[126],"high":[127],"deception":[128],"performance":[129],"against":[130],"humans.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
