{"id":"https://openalex.org/W2117544888","doi":"https://doi.org/10.1109/tasl.2012.2201472","title":"Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech","display_name":"Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech","publication_year":2012,"publication_date":"2012-05-29","ids":{"openalex":"https://openalex.org/W2117544888","doi":"https://doi.org/10.1109/tasl.2012.2201472","mag":"2117544888"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2201472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2201472","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030748919","display_name":"Phillip L. De Le\u00f3n","orcid":"https://orcid.org/0000-0002-7665-9632"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Phillip L. De Leon","raw_affiliation_strings":["Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA","Klipsch School of Electrical and Computer Engineering, New Mexico State University (NMSU), Las Cruces, NM, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]},{"raw_affiliation_string":"Klipsch School of Electrical and Computer Engineering, New Mexico State University (NMSU), Las Cruces, NM, USA#TAB#","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088212404","display_name":"Michael Pucher","orcid":"https://orcid.org/0000-0002-5374-1342"},"institutions":[{"id":"https://openalex.org/I4210122474","display_name":"Forschungszentrum Telekommunikation Wien","ror":"https://ror.org/026nftk33","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210122474"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Pucher","raw_affiliation_strings":["Telecommunications Research Center Vienna (FTW), Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Telecommunications Research Center Vienna (FTW), Vienna, Austria","institution_ids":["https://openalex.org/I4210122474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK","University of Edinburgh, edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh, edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049169182","display_name":"Inma Hern\u00e1ez","orcid":"https://orcid.org/0000-0003-4447-7575"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Inma Hernaez","raw_affiliation_strings":["University of Basque Country (UPV-EHU), Bilbao, Spain","University of the Basque Country, Bilbao, Spain"],"affiliations":[{"raw_affiliation_string":"University of Basque Country (UPV-EHU), Bilbao, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"University of the Basque Country, Bilbao, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022483971","display_name":"Ibon Saratxaga","orcid":"https://orcid.org/0000-0001-7282-2765"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ibon Saratxaga","raw_affiliation_strings":["University of Basque Country (UPV-EHU), Bilbao, Spain","University of the Basque Country, Bilbao, Spain"],"affiliations":[{"raw_affiliation_string":"University of Basque Country (UPV-EHU), Bilbao, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"University of the Basque Country, Bilbao, Spain","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030748919"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":21.085,"has_fulltext":false,"cited_by_count":231,"citation_normalized_percentile":{"value":0.99485094,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"20","issue":"8","first_page":"2280","last_page":"2290"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9865000247955322,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8437743782997131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8117923140525818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794281244277954},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6316568851470947},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5701263546943665},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5380541682243347},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5163158774375916},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5070760250091553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49936366081237793},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4749222695827484},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4616277515888214},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4407919943332672},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4393174350261688},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4295293688774109},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42175647616386414}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8437743782997131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8117923140525818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794281244277954},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6316568851470947},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5701263546943665},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5380541682243347},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5163158774375916},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5070760250091553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49936366081237793},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4749222695827484},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4616277515888214},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4407919943332672},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4393174350261688},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4295293688774109},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42175647616386414}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2012.2201472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2201472","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","pdf_url":"http://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"De Leon, P L, Pucher, M, Yamagishi, J, Hernaez, I & Saratxaga, I 2012, 'Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech', IEEE Transactions on Audio, Speech and Language Processing, vol. 20, no. 8, pp. 2280-2290. https://doi.org/10.1109/TASL.2012.2201472","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","pdf_url":"http://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","pdf_url":"http://hdl.handle.net/20.500.11820/d5814bab-5fc2-4c31-92b7-543c7ce75cb4","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"De Leon, P L, Pucher, M, Yamagishi, J, Hernaez, I & Saratxaga, I 2012, 'Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech', IEEE Transactions on Audio, Speech and Language Processing, vol. 20, no. 8, pp. 2280-2290. https://doi.org/10.1109/TASL.2012.2201472","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2117544888.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W8362967","https://openalex.org/W11511395","https://openalex.org/W95551363","https://openalex.org/W118156158","https://openalex.org/W174866149","https://openalex.org/W204204962","https://openalex.org/W1550612414","https://openalex.org/W1557133539","https://openalex.org/W1564152904","https://openalex.org/W1565240090","https://openalex.org/W1569585975","https://openalex.org/W1572730534","https://openalex.org/W1599512239","https://openalex.org/W1604510059","https://openalex.org/W1707026573","https://openalex.org/W1963627370","https://openalex.org/W1967797949","https://openalex.org/W1969876212","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2023847438","https://openalex.org/W2024490156","https://openalex.org/W2041823554","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2078953162","https://openalex.org/W2093450784","https://openalex.org/W2096555739","https://openalex.org/W2099124598","https://openalex.org/W2106792148","https://openalex.org/W2112659417","https://openalex.org/W2117418893","https://openalex.org/W2119929864","https://openalex.org/W2121750345","https://openalex.org/W2124783762","https://openalex.org/W2129142580","https://openalex.org/W2133420453","https://openalex.org/W2143597468","https://openalex.org/W2143803185","https://openalex.org/W2144139079","https://openalex.org/W2144760012","https://openalex.org/W2145892079","https://openalex.org/W2146621297","https://openalex.org/W2147147599","https://openalex.org/W2153541119","https://openalex.org/W2153914468","https://openalex.org/W2161919410","https://openalex.org/W2165143604","https://openalex.org/W2395578248","https://openalex.org/W2397634864","https://openalex.org/W2428180336","https://openalex.org/W2770865485","https://openalex.org/W3146606878","https://openalex.org/W4213154530","https://openalex.org/W6604808977","https://openalex.org/W6607058271","https://openalex.org/W6608211636","https://openalex.org/W6632908759","https://openalex.org/W6633604485","https://openalex.org/W6633741138","https://openalex.org/W6711777497","https://openalex.org/W6712325649","https://openalex.org/W6746742183","https://openalex.org/W6865107258"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0],"this":[1,145],"paper,":[2],"we":[3],"evaluate":[4],"the":[5,22,72,94,104],"vulnerability":[6,112],"of":[7,58,64,103,139,153],"speaker":[8,54,90],"verification":[9],"(SV)":[10],"systems":[11,17,74,115],"to":[12,120,150],"synthetic":[13,86,123,140],"speech.":[14,124],"The":[15],"SV":[16,73,114,154],"are":[18,107],"based":[19,130],"on":[20,131],"either":[21],"Gaussian":[23],"mixture":[24],"model\u2013universal":[25],"background":[26,69],"model":[27,42,62],"(GMM-UBM)":[28],"or":[29,68],"support":[30],"vector":[31],"machine":[32],"(SVM)":[33],"using":[34,55],"GMM":[35],"supervectors.":[36],"We":[37,125],"use":[38],"a":[39,52,76,118,127],"hidden":[40],"Markov":[41],"(HMM)-based":[43],"text-to-speech":[44],"(TTS)":[45],"synthesizer,":[46],"which":[47],"can":[48,147],"synthesize":[49],"speech":[50,87,99],"for":[51],"target":[53],"small":[56],"amounts":[57],"training":[59],"data":[60],"through":[61],"adaptation":[63],"an":[65],"average":[66],"voice":[67],"model.":[70],"Although":[71],"have":[75],"very":[77],"low":[78],"equal":[79],"error":[80],"rate":[81],"(EER),":[82],"when":[83],"tested":[84],"with":[85],"generated":[88],"from":[89,93],"models":[91],"derived":[92],"Wall":[95],"Street":[96],"Journal":[97],"(WSJ)":[98],"corpus,":[100],"over":[101],"81%":[102],"matched":[105],"claims":[106],"accepted.":[108],"This":[109],"result":[110],"suggests":[111],"in":[113],"and":[116,142],"thus":[117],"need":[119],"accurately":[121],"detect":[122],"propose":[126],"new":[128],"feature":[129],"relative":[132],"phase":[133],"shift":[134],"(RPS),":[135],"demonstrate":[136],"reliable":[137],"detection":[138],"speech,":[141],"show":[143],"how":[144],"classifier":[146],"be":[148],"used":[149],"improve":[151],"security":[152],"systems.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}