{"id":"https://openalex.org/W4416799218","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249218","title":"Study on Signal Processing Techniques in Protecting Voice Personae Against Speech Synthesis Systems","display_name":"Study on Signal Processing Techniques in Protecting Voice Personae Against Speech Synthesis Systems","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799218","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249218"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5059249923","display_name":"Ning Li","orcid":"https://orcid.org/0009-0002-8186-5091"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nopparut Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Candy Olivia Mawalim","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17292552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"759","last_page":"764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8019000291824341,"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":0.8019000291824341,"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":0.06639999896287918,"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/T11448","display_name":"Face recognition and analysis","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-synthesis","display_name":"Speech synthesis","score":0.6868000030517578},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6743000149726868},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5679000020027161},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4359000027179718},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4350999891757965},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.41999998688697815},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8082000017166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451000213623047},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6868000030517578},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6743000149726868},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4359000027179718},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.41999998688697815},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G282263216","display_name":null,"funder_award_id":"JPMJSF2318","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067295501","https://openalex.org/W2073347271","https://openalex.org/W2972659941","https://openalex.org/W3143465836","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W3205878676","https://openalex.org/W4225420087","https://openalex.org/W4388856757"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"speech":[3,11,38,81,98,114,120,131],"synthesis":[4,132],"have":[5,34],"enabled":[6],"the":[7,23,47,74,77,85,92,96,103,110],"generation":[8],"of":[9,25,79,95,112],"natural-sounding":[10],"signals":[12,82,115],"that":[13,102],"can":[14,41],"closely":[15],"mimic":[16],"specific":[17],"speakers,":[18],"raising":[19],"serious":[20],"concerns":[21],"about":[22],"misuse":[24],"voice":[26,127],"recordings":[27],"for":[28,73,126],"impersonation":[29],"and":[30,64,70],"fraud.":[31],"Although":[32],"researchers":[33],"extensively":[35],"studied":[36],"spoof":[37],"detection,":[39],"they":[40],"only":[42],"implement":[43],"these":[44],"approaches":[45],"once":[46],"spoofed":[48],"content":[49],"has":[50],"been":[51],"generated.":[52],"We":[53],"propose":[54],"a":[55,123],"method":[56,105],"based":[57],"on":[58,76,119],"<tex":[59],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[60],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$F_{0}$</tex>":[61],"component":[62],"elimination":[63],"compare":[65],"it":[66],"with":[67,116],"conventional":[68],"filtering":[69],"artificial":[71],"reverberation":[72],"impact":[75,118],"quality":[78,94],"synthesized":[80,113],"generated":[83],"using":[84],"TorToiSe":[86],"TTS":[87],"model,":[88],"as":[89,91],"well":[90],"perceptual":[93],"modified":[97],"signals.":[99],"Results":[100],"show":[101],"proposed":[104],"is":[106],"able":[107],"to":[108],"reduce":[109],"identifiability":[111],"minimal":[117],"quality,":[121],"offering":[122],"promising":[124],"direction":[125],"personae":[128],"protection":[129],"against":[130],"systems.":[133]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}
