{"id":"https://openalex.org/W2573756443","doi":"https://doi.org/10.2352/issn.2470-1173.2016.8.mwsf-073","title":"Attacks on Speaker Identification Systems Constrained to Speech-to-Text Decoding","display_name":"Attacks on Speaker Identification Systems Constrained to Speech-to-Text Decoding","publication_year":2016,"publication_date":"2016-02-14","ids":{"openalex":"https://openalex.org/W2573756443","doi":"https://doi.org/10.2352/issn.2470-1173.2016.8.mwsf-073","mag":"2573756443"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2016.8.mwsf-073","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.8.mwsf-073","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-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/A5051591592","display_name":"Alireza Farrokh Baroughi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alireza Farrokh Baroughi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066468477","display_name":"Scott Craver","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Craver","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060889762","display_name":"Daniel Douglas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Douglas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0895841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"8","first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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":0.9937999844551086,"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":0.9873999953269958,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9133999943733215,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.818712592124939},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.777376651763916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592848539352417},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7321312427520752},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.627588152885437},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.624153733253479},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5748490691184998},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.520315408706665},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4927199184894562},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4762280583381653},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.46313241124153137},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4592558741569519},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4438019394874573},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.43116968870162964},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41843998432159424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3554776906967163},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.19396358728408813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12051934003829956}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.818712592124939},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.777376651763916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592848539352417},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7321312427520752},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.627588152885437},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.624153733253479},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5748490691184998},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.520315408706665},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4927199184894562},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4762280583381653},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.46313241124153137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4592558741569519},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4438019394874573},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.43116968870162964},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41843998432159424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3554776906967163},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19396358728408813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12051934003829956},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2016.8.mwsf-073","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.8.mwsf-073","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W3204851989","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Speech":[0],"processing":[1],"is":[2],"used":[3,80,101,112],"to":[4,8,11,24,89],"translate":[5],"human":[6],"speech":[7,110,114],"text":[9],"and":[10,73],"identify":[12],"speakers":[13],"for":[14,84,102,113],"applications":[15,83],"in":[16,81,94],"biometric":[17],"systems.":[18],"Speaker":[19],"verification":[20,64],"requires":[21],"robust":[22],"algorithms":[23],"prohibit":[25],"an":[26],"adversary":[27],"from":[28],"impersonating":[29],"another":[30,109],"speaker.":[31],"Previous":[32],"research":[33],"has":[34],"demonstrated":[35],"that":[36],"specially":[37],"crafted":[38],"additive":[39,59],"noise":[40,60],"can":[41,61],"cause":[42],"a":[43,46,49,91],"misclassification":[44],"of":[45,97],"speaker":[47,63,99,103],"as":[48],"specific":[50],"target.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"study":[56],"whether":[57],"targeted":[58],"thwart":[62],"without":[65],"affecting":[66],"speech-to-text":[67],"decoding.":[68,115],"Mel-frequency":[69],"cepstral":[70],"coefficients":[71],"(MFCCs)":[72],"Gaussian":[74],"mixture":[75],"models":[76],"(GMMs)":[77],"are":[78],"commonly":[79],"both":[82],"encoding":[85],"schemes.":[86],"We":[87],"attempt":[88],"induce":[90],"desired":[92],"change":[93],"the":[95],"probability":[96],"one":[98],"model":[100,111],"classification,":[104],"while":[105],"preserving":[106],"likelihood":[107],"under":[108]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}