{"id":"https://openalex.org/W4390479006","doi":"https://doi.org/10.1145/3595916.3626366","title":"Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization","display_name":"Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479006","doi":"https://doi.org/10.1145/3595916.3626366"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626366","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103093817","display_name":"Xiaojiao Chen","orcid":"https://orcid.org/0000-0002-5458-7025"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiao Chen","raw_affiliation_strings":["Xinjiang University, CN"],"raw_orcid":"https://orcid.org/0000-0002-5458-7025","affiliations":[{"raw_affiliation_string":"Xinjiang University, CN","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), JP"],"raw_orcid":"https://orcid.org/0000-0001-7636-3797","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), JP","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067208985","display_name":"Jiyi Li","orcid":"https://orcid.org/0000-0003-4997-3850"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiyi Li","raw_affiliation_strings":["University of Yamanashi, JP"],"raw_orcid":"https://orcid.org/0000-0003-4997-3850","affiliations":[{"raw_affiliation_string":"University of Yamanashi, JP","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University, CN"],"raw_orcid":"https://orcid.org/0000-0001-6604-0951","affiliations":[{"raw_affiliation_string":"Xinjiang University, CN","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082946615","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-6424-8633"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":["Hokkaido University, JP"],"raw_orcid":"https://orcid.org/0000-0002-6424-8633","affiliations":[{"raw_affiliation_string":"Hokkaido University, JP","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"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":"Liang He","raw_affiliation_strings":["Tsinghua University, CN"],"raw_orcid":"https://orcid.org/0000-0003-4076-7479","affiliations":[{"raw_affiliation_string":"Tsinghua University, CN","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.8177310228347778},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6512411236763},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.609565258026123},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5936000347137451},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45360079407691956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4511028826236725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42837047576904297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07088586688041687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177310228347778},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6512411236763},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.609565258026123},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5936000347137451},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45360079407691956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4511028826236725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42837047576904297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07088586688041687},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4390204761","display_name":null,"funder_award_id":"JP23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5208785282","display_name":"Learning Reliable Deep Models from Noise Labels by Crowdsourcing","funder_award_id":"23K28092","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479006.pdf","grobid_xml":"https://content.openalex.org/works/W4390479006.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2797978264","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W3092028330","https://openalex.org/W3096424617","https://openalex.org/W3180600971","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206231964","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2276249771","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"Current":[0],"speaker":[1,16,25,43,51,61,66],"anonymization":[2,26,38,92],"methods,":[3],"especially":[4],"with":[5,99],"self-supervised":[6],"learning":[7,91],"(SSL)":[8],"models,":[9],"require":[10],"massive":[11],"computational":[12,111],"resources":[13,112],"when":[14],"hiding":[15],"identity.":[17],"This":[18],"paper":[19],"proposes":[20],"an":[21],"effective":[22],"and":[23],"parameter-efficient":[24,90],"method":[27],"based":[28],"on":[29,76],"recent":[30],"End-to-End":[31],"model":[32],"reprogramming":[33],"technology.":[34],"To":[35,53],"improve":[36],"the":[37,50,55,60,65,77,85,100],"performance,":[39],"we":[40,58],"first":[41],"extract":[42],"representation":[44,62],"from":[45],"large":[46],"SSL":[47],"models":[48],"as":[49],"identifies.":[52],"hide":[54],"speaker\u2019s":[56],"identity,":[57],"reprogram":[59],"by":[63],"adapting":[64],"to":[67,83],"a":[68],"pseudo":[69],"domain.":[70],"Extensive":[71],"experiments":[72],"are":[73],"carried":[74],"out":[75],"VoicePrivacy":[78],"Challenge":[79],"(VPC)":[80],"2022":[81,102],"datasets":[82],"demonstrate":[84],"effectiveness":[86],"of":[87],"our":[88,106],"proposed":[89],"methods.":[93],"Additionally,":[94],"while":[95],"achieving":[96],"comparable":[97],"performance":[98],"VPC":[101],"strong":[103],"baseline":[104],"1.b,":[105],"approach":[107],"also":[108],"consumes":[109],"less":[110],"during":[113],"anonymization.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}