{"id":"https://openalex.org/W4372260248","doi":"https://doi.org/10.1109/icassp49357.2023.10096607","title":"Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning","display_name":"Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260248","doi":"https://doi.org/10.1109/icassp49357.2023.10096607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096607","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/A5064340157","display_name":"Sarina Meyer","orcid":"https://orcid.org/0009-0004-1117-4783"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sarina Meyer","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082226616","display_name":"Julia Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Koch","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081451455","display_name":"Pavel Denisov","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pavel Denisov","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091791731","display_name":"Pascal Tilli","orcid":"https://orcid.org/0009-0001-7503-1413"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pascal Tilli","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["Institute for Natural Language Processing,University of Stuttgart,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing,University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064340157"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":3.9972,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94893857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/prosody","display_name":"Prosody","score":0.9135729074478149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7480860352516174},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6642740964889526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6497262120246887},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5906747579574585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3847326636314392},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37488681077957153}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9135729074478149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480860352516174},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6642740964889526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6497262120246887},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5906747579574585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847326636314392},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37488681077957153},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096607","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2794490148","https://openalex.org/W2803193013","https://openalex.org/W2972359262","https://openalex.org/W2991440249","https://openalex.org/W2998572311","https://openalex.org/W3034949308","https://openalex.org/W3081871358","https://openalex.org/W3150572638","https://openalex.org/W3163573274","https://openalex.org/W3196321886","https://openalex.org/W3216758611","https://openalex.org/W4210970267","https://openalex.org/W4225585117","https://openalex.org/W4281250109","https://openalex.org/W4284973286","https://openalex.org/W4285189120","https://openalex.org/W4292597003","https://openalex.org/W4296069300","https://openalex.org/W4297904260","https://openalex.org/W4319862433","https://openalex.org/W4319862723","https://openalex.org/W4395961059","https://openalex.org/W6750489868","https://openalex.org/W6772349387","https://openalex.org/W6784688130","https://openalex.org/W6810404315","https://openalex.org/W6839026989","https://openalex.org/W6842148106","https://openalex.org/W6843630785","https://openalex.org/W6845852016","https://openalex.org/W6849520149","https://openalex.org/W6857434696"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W3008088358","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4400309480"],"abstract_inverted_index":{"Prosody":[0],"is":[1,19],"closely":[2],"linked":[3],"to":[4,11,24,61,84,109],"the":[5,31,39,63,87,102,105,111],"identity":[6],"of":[7],"a":[8,47,51,122],"speaker,":[9],"leading":[10],"individual":[12],"pitch":[13,67,98],"and":[14,37,58,68,77,96,115,120],"intonation":[15],"patterns.":[16],"Therefore,":[17],"it":[18],"challenging":[20],"in":[21,125],"speaker":[22],"anonymization":[23,53],"generate":[25],"speech":[26],"utterances":[27,107],"that":[28,49],"both":[29],"keep":[30],"original":[32,112],"audio\u2019s":[33],"main":[34],"prosodic":[35],"structure":[36],"preserve":[38],"speaker\u2019s":[40],"privacy.":[41],"In":[42],"this":[43,82],"paper,":[44],"we":[45,80],"present":[46],"system":[48],"extends":[50],"speech-to-text-to-speech":[52],"pipeline":[54],"with":[55,71,117],"prosody":[56,91],"cloning":[57,64],"show":[59],"how":[60],"control":[62],"by":[65,92],"multiplying":[66],"energy":[69],"sequences":[70],"random":[72],"offset":[73],"values.":[74],"Using":[75],"automatic":[76],"human":[78],"evaluation,":[79],"find":[81],"combination":[83],"successfully":[85],"overcome":[86],"privacy-utility":[88],"trade-off":[89],"for":[90,130],"achieving":[93],"high":[94,97,118],"privacy":[95],"correlation":[99],"scores.":[100],"At":[101],"same":[103],"time,":[104],"anonymized":[106],"prove":[108],"reproduce":[110],"voice":[113],"distinctiveness":[114],"content":[116],"intelligibility":[119],"only":[121],"small":[123],"loss":[124],"naturalness,":[126],"making":[127],"them":[128],"suitable":[129],"downstream":[131],"applications.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
