{"id":"https://openalex.org/W4372267192","doi":"https://doi.org/10.1109/icassp49357.2023.10095120","title":"Distinguishable Speaker Anonymization Based on Formant and Fundamental Frequency Scaling","display_name":"Distinguishable Speaker Anonymization Based on Formant and Fundamental Frequency Scaling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267192","doi":"https://doi.org/10.1109/icassp49357.2023.10095120"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015560758","display_name":"Jixun Yao","orcid":"https://orcid.org/0000-0002-5324-7360"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808955","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0008-5449-4815"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013928267","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0002-9256-9311"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024196194","display_name":"Namin Wang","orcid":"https://orcid.org/0009-0004-1504-4345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namin Wang","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454052","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0002-0750-1030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3053,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83802372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/formant","display_name":"Formant","score":0.8182163834571838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7855715155601501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6630847454071045},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5085517168045044},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5019989013671875},{"id":"https://openalex.org/keywords/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.47054582834243774},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4369683265686035},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42592141032218933},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41847342252731323},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.41711774468421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21631532907485962},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10847312211990356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09081500768661499}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8182163834571838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855715155601501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6630847454071045},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5085517168045044},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5019989013671875},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.47054582834243774},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4369683265686035},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42592141032218933},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41847342252731323},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.41711774468421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21631532907485962},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10847312211990356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09081500768661499},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2031529434","https://openalex.org/W2091425152","https://openalex.org/W2140567543","https://openalex.org/W2527729766","https://openalex.org/W2954217241","https://openalex.org/W2963609956","https://openalex.org/W2972359262","https://openalex.org/W2972848589","https://openalex.org/W3043999252","https://openalex.org/W3081871358","https://openalex.org/W3096424617","https://openalex.org/W3144035034","https://openalex.org/W3180600971","https://openalex.org/W3196623473","https://openalex.org/W3197008493","https://openalex.org/W3197478142","https://openalex.org/W4210970267","https://openalex.org/W4221114270","https://openalex.org/W4296069300","https://openalex.org/W4297437784","https://openalex.org/W4297841874","https://openalex.org/W6727697161","https://openalex.org/W6783867762","https://openalex.org/W6839738141","https://openalex.org/W6843253040","https://openalex.org/W6843630785"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speech":[0],"data":[1,21],"on":[2],"the":[3,10,16,71,80,85,89,104,117,121,130,134,139,144,161,180],"Internet":[4],"are":[5],"proliferating":[6],"exponentially":[7],"because":[8],"of":[9,12,18,88,138,146],"emergence":[11],"social":[13],"media,":[14],"and":[15,25,107,115,125,132,164],"sharing":[17,39],"such":[19],"personal":[20],"raises":[22],"obvious":[23],"security":[24],"privacy":[26,65],"concerns.":[27],"One":[28],"solution":[29],"to":[30,44,62,111],"mitigate":[31],"these":[32],"concerns":[33],"involves":[34],"concealing":[35],"speaker":[36,46,57,64,86,113,135,162],"identities":[37],"before":[38],"speech":[40,68,91,119,141],"data,":[41],"also":[42],"referred":[43],"as":[45],"anonymization.":[47],"In":[48],"our":[49,156,167,174],"previous":[50,168],"work,":[51],"we":[52,101],"have":[53],"developed":[54],"an":[55],"automatic":[56],"verification":[58],"(ASV)-model-free":[59],"anonymization":[60,81],"framework":[61,72,158,169],"protect":[63],"while":[66],"preserving":[67],"intelligibility.":[69],"Although":[70],"ranked":[73],"first":[74],"place":[75],"in":[76,98,170],"VoicePrivacy":[77],"2022":[78],"challenge,":[79],"was":[82,92],"imperfect,":[83],"since":[84],"distinguishability":[87,136,163],"anonymized":[90,140],"deteriorated.":[93],"To":[94],"address":[95],"this":[96,99],"issue,":[97],"paper,":[100],"directly":[102,128],"model":[103],"formant":[105,124,131],"distribution":[106],"fundamental":[108],"frequency":[109],"(F0)":[110],"represent":[112],"identity":[114],"anonymize":[116],"source":[118],"by":[120,143,182],"uniformly":[122],"scaling":[123,129,185],"F0.":[126],"By":[127],"F0,":[133],"degradation":[137],"caused":[142],"introduction":[145],"other":[147],"speakers":[148],"is":[149],"prevented.":[150],"The":[151],"experimental":[152],"results":[153],"demonstrate":[154],"that":[155],"proposed":[157,175],"can":[159,177],"improve":[160],"significantly":[165],"outperforms":[166],"voice":[171],"distinctiveness.":[172],"Furthermore,":[173],"method":[176],"trade":[178],"off":[179],"privacy-utility":[181],"using":[183],"different":[184],"factors.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
