{"id":"https://openalex.org/W2185901580","doi":"https://doi.org/10.21437/odyssey.2014-13","title":"Comparison of human listeners and speaker verification systems using voice mimicry data","display_name":"Comparison of human listeners and speaker verification systems using voice mimicry data","publication_year":2014,"publication_date":"2014-06-16","ids":{"openalex":"https://openalex.org/W2185901580","doi":"https://doi.org/10.21437/odyssey.2014-13","mag":"2185901580"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2014-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","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/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038242813","display_name":"Rosa Gonz\u00e1lez Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-4140-5309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rosa Gonzalez Hautam\u00e4ki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020118580","display_name":"Anne-Maria Laukkanen","orcid":"https://orcid.org/0000-0003-4836-2513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anne-Maria Laukkanen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037259225"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2721,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93161921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"144"},"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":0.9991999864578247,"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":0.9966999888420105,"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/mimicry","display_name":"Mimicry","score":0.8049197793006897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794283628463745},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.737758994102478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7108821868896484},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6289548277854919},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.516964852809906},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5082085132598877},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48472142219543457},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47517767548561096},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4650624394416809},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44879215955734253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4317163825035095}],"concepts":[{"id":"https://openalex.org/C7863114","wikidata":"https://www.wikidata.org/wiki/Q192627","display_name":"Mimicry","level":2,"score":0.8049197793006897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794283628463745},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.737758994102478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7108821868896484},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6289548277854919},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.516964852809906},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5082085132598877},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48472142219543457},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47517767548561096},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4650624394416809},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44879215955734253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4317163825035095},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2014-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W75992864","https://openalex.org/W761025340","https://openalex.org/W1490120479","https://openalex.org/W1495679096","https://openalex.org/W1497681771","https://openalex.org/W1533303231","https://openalex.org/W1550612414","https://openalex.org/W1593282153","https://openalex.org/W1596996860","https://openalex.org/W2041823554","https://openalex.org/W2046873783","https://openalex.org/W2112606109","https://openalex.org/W2114499274","https://openalex.org/W2117544888","https://openalex.org/W2121973264","https://openalex.org/W2128466129","https://openalex.org/W2129272077","https://openalex.org/W2129312524","https://openalex.org/W2130813098","https://openalex.org/W2137591261","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2293407848","https://openalex.org/W2294192652","https://openalex.org/W2395750323","https://openalex.org/W2407374891","https://openalex.org/W2468858848"],"related_works":["https://openalex.org/W2963560054","https://openalex.org/W2018623685","https://openalex.org/W66821593","https://openalex.org/W4306406306","https://openalex.org/W1521299571","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2316548414","https://openalex.org/W4235705411","https://openalex.org/W1992796048"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"compare":[4,41],"the":[5,44,71,77,85,93,97,108,113,122,125,131,139,181,188],"performance":[6,46,95,137],"of":[7,19,47,96,115,124,133,138],"human":[8,31,140],"listeners":[9,32],"and":[10,40,60],"two":[11],"well":[12,30],"known":[13],"speaker":[14,49,126],"verification":[15,50,127],"systems":[16,128,183],"in":[17,74,88,118,130,187],"presence":[18,132],"voice":[20],"mimicry.":[21],"Our":[22,103],"focus":[23],"is":[24,38,148,160],"to":[25,43,82,101,150,155,163],"gain":[26],"insights":[27],"on":[28],"how":[29],"recognize":[33,156],"speakers":[34],"when":[35],"mimicry":[36,78],"data":[37,104,116],"included":[39],"it":[42],"overall":[45],"state-ofthe-art":[48],"systems,":[51],"a":[52,89,157],"traditional":[53],"Gaussian":[54],"mixture":[55],"model-universal":[56],"background":[57],"model":[58],"(GMM-UBM)":[59],"an":[61],"i-vector":[62],"based":[63],"classifier":[64],"withcosine":[65],"scoring.":[66],"Wehave":[67],"found":[68],"that":[69,106,144],"for":[70,92],"studied":[72],"material":[73,110],"Finnish":[75],"language,":[76],"attack":[79],"was":[80],"able":[81],"slightly":[83],"increase":[84],"error":[86,186],"rate":[87],"range":[90],"acceptable":[91],"general":[94],"system":[98],"(EERfrom":[99],"9":[100],"11%).":[102],"reveals":[105],"enhancing":[107],"audio":[109],"by":[111],"minimizing":[112],"differences":[114],"collected":[117],"different":[119],"environments":[120],"improves":[121],"accuracy":[123],"even":[129,152],"mimicked":[134],"speech.":[135],"The":[136,170],"listening":[141],"panel":[142],"shows":[143],"successfully":[145],"imitated":[146],"speech":[147],"difficult":[149,154],"recognize,":[151],"more":[153],"person":[158],"who":[159],"intentionally":[161],"trying":[162],"modify":[164],"his":[165],"or":[166],"her":[167],"own":[168],"voice.":[169],"average":[171],"listener":[172],"made":[173],"8":[174],"errors":[175],"from":[176],"34":[177],"selected":[178],"trials":[179],"while":[180],"automatic":[182],"had":[184],"6":[185],"same":[189],"set.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}