{"id":"https://openalex.org/W4391021726","doi":"https://doi.org/10.1109/asru57964.2023.10389719","title":"Salt: Distinguishable Speaker Anonymization Through Latent Space Transformation","display_name":"Salt: Distinguishable Speaker Anonymization Through Latent Space Transformation","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021726","doi":"https://doi.org/10.1109/asru57964.2023.10389719"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5108604484","display_name":"Yuanjun Lv","orcid":"https://orcid.org/0009-0002-2272-9153"},"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":"Yuanjun Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","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&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085355820","display_name":"Peikun Chen","orcid":null},"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":"Peikun Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;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&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110823442","display_name":"Hongbin Zhou","orcid":"https://orcid.org/0009-0005-7569-1197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Zhou","raw_affiliation_strings":["Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc., China Xizhang (Shanghai) Network Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","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&#x0040;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&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1421,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8332031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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":0.7559876441955566},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.658208966255188},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5932581424713135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5713249444961548},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46441882848739624},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.448797345161438},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.42936229705810547},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3493356704711914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3483268618583679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559876441955566},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.658208966255188},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5932581424713135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5713249444961548},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46441882848739624},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.448797345161438},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.42936229705810547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3493356704711914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483268618583679},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W139084513","https://openalex.org/W1494198834","https://openalex.org/W2790046776","https://openalex.org/W2888867175","https://openalex.org/W2972848589","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3081871358","https://openalex.org/W3094544164","https://openalex.org/W3096424617","https://openalex.org/W3122079819","https://openalex.org/W3167533889","https://openalex.org/W3170405627","https://openalex.org/W3197478142","https://openalex.org/W3198694222","https://openalex.org/W3201497420","https://openalex.org/W3209984917","https://openalex.org/W4225585117","https://openalex.org/W4245692952","https://openalex.org/W4295308567","https://openalex.org/W4296069300","https://openalex.org/W4297437784","https://openalex.org/W4306867200","https://openalex.org/W4311000453","https://openalex.org/W4385823432","https://openalex.org/W6765696844","https://openalex.org/W6783867762","https://openalex.org/W6784635364","https://openalex.org/W6788095198","https://openalex.org/W6791179763","https://openalex.org/W6797037654","https://openalex.org/W6810404315","https://openalex.org/W6843253040","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0,63],"anonymization":[1,16,28],"aims":[2],"to":[3,42,95,105],"conceal":[4],"a":[5,62,77,123],"speaker\u2019s":[6],"identity":[7],"without":[8],"degrading":[9],"speech":[10,25,39,48,129],"quality":[11,49,130],"and":[12,26,50,81,86,89,131,135],"intelligibility.":[13,132],"Most":[14],"speaker":[15,20,34,46,97],"systems":[17],"disentangle":[18],"the":[19,23,33,37,92,102,108],"representation":[21],"from":[22],"original":[24],"achieve":[27,96],"by":[29,76],"averaging":[30],"or":[31],"modifying":[32],"representation.":[35],"However,":[36],"anonymized":[38],"is":[40,137],"subject":[41],"reduction":[43],"in":[44],"pseudo":[45,111],"distinctiveness,":[47],"intelligibility":[51],"for":[52],"out-of-distribution":[53],"speaker.":[54],"To":[55],"solve":[56],"this":[57],"issue,":[58],"we":[59,72,100],"propose":[60],"SALT,":[61],"Anonymization":[64],"system":[65,121],"based":[66],"on":[67,114],"Latent":[68],"space":[69],"Transformation.":[70],"Specifically,":[71],"extract":[73],"latent":[74,93],"features":[75],"self-supervised":[78],"feature":[79],"extractor":[80],"randomly":[82],"sample":[83],"multiple":[84],"speakers":[85],"their":[87],"weights,":[88],"then":[90],"interpolate":[91],"vectors":[94],"anonymization.":[98],"Meanwhile,":[99],"explore":[101],"extrapolation":[103],"method":[104],"further":[106],"extend":[107],"diversity":[109],"of":[110],"speakers.":[112],"Experiments":[113],"Voice":[115],"Privacy":[116],"Challenge":[117],"dataset":[118],"show":[119],"our":[120],"achieves":[122],"state-of-the-art":[124],"distinctiveness":[125],"metric":[126],"while":[127],"preserving":[128],"Our":[133],"code":[134],"demo":[136],"availible":[138],"at":[139],"github":[140],"<sup":[141,145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[142,146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[143,147],".":[144],"https://github.com/BakerBunker/SALT":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
