{"id":"https://openalex.org/W2921830315","doi":"https://doi.org/10.1117/12.2523138","title":"Bimodal person identification using voice data and face images","display_name":"Bimodal person identification using voice data and face images","publication_year":2019,"publication_date":"2019-03-15","ids":{"openalex":"https://openalex.org/W2921830315","doi":"https://doi.org/10.1117/12.2523138","mag":"2921830315"},"language":"en","primary_location":{"id":"doi:10.1117/12.2523138","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2523138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eleventh International Conference on Machine Vision (ICMV 2018)","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/A5082955665","display_name":"Vladimir Khryashchev","orcid":"https://orcid.org/0000-0003-2978-2459"},"institutions":[{"id":"https://openalex.org/I198371094","display_name":"Yaroslavl State University","ror":"https://ror.org/044s2fj67","country_code":"RU","type":"education","lineage":["https://openalex.org/I198371094"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vladimir Khryashchev","raw_affiliation_strings":["P.G. Demidov Yaroslavl State Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"P.G. Demidov Yaroslavl State Univ. (Russian Federation)","institution_ids":["https://openalex.org/I198371094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086163007","display_name":"Artem Topnikov","orcid":null},"institutions":[{"id":"https://openalex.org/I198371094","display_name":"Yaroslavl State University","ror":"https://ror.org/044s2fj67","country_code":"RU","type":"education","lineage":["https://openalex.org/I198371094"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. I. Topnikov","raw_affiliation_strings":["P.G. Demidov Yaroslavl State Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"P.G. Demidov Yaroslavl State Univ. (Russian Federation)","institution_ids":["https://openalex.org/I198371094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004969008","display_name":"Anton Stefanidi","orcid":null},"institutions":[{"id":"https://openalex.org/I198371094","display_name":"Yaroslavl State University","ror":"https://ror.org/044s2fj67","country_code":"RU","type":"education","lineage":["https://openalex.org/I198371094"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. F. Stefanidi","raw_affiliation_strings":["P.G. Demidov Yaroslavl State Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"P.G. Demidov Yaroslavl State Univ. (Russian Federation)","institution_ids":["https://openalex.org/I198371094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008189781","display_name":"Andrey Priorov","orcid":"https://orcid.org/0000-0003-2984-340X"},"institutions":[{"id":"https://openalex.org/I198371094","display_name":"Yaroslavl State University","ror":"https://ror.org/044s2fj67","country_code":"RU","type":"education","lineage":["https://openalex.org/I198371094"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. L. Priorov","raw_affiliation_strings":["P.G. Demidov Yaroslavl State Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"P.G. Demidov Yaroslavl State Univ. (Russian Federation)","institution_ids":["https://openalex.org/I198371094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082955665"],"corresponding_institution_ids":["https://openalex.org/I198371094"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51265095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"52","issue":null,"first_page":"98","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.6717740297317505},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6525744199752808},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6400948762893677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5585010051727295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47696933150291443},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4705650806427002},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4100019335746765},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38839101791381836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31432631611824036},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24454039335250854},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09481477737426758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717740297317505},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6525744199752808},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6400948762893677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5585010051727295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47696933150291443},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4705650806427002},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4100019335746765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38839101791381836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31432631611824036},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24454039335250854},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09481477737426758},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2523138","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2523138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eleventh International Conference on Machine Vision (ICMV 2018)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W102958777","https://openalex.org/W1585588639","https://openalex.org/W1966635716","https://openalex.org/W2024677982","https://openalex.org/W2041823554","https://openalex.org/W2119970915","https://openalex.org/W2127884747","https://openalex.org/W2140609507","https://openalex.org/W2158275940","https://openalex.org/W2166817508","https://openalex.org/W2184045248","https://openalex.org/W2337287328","https://openalex.org/W2608941919","https://openalex.org/W4231210906","https://openalex.org/W6635024482","https://openalex.org/W6680902425","https://openalex.org/W6681342084","https://openalex.org/W6683671510","https://openalex.org/W6686210252","https://openalex.org/W6700903540","https://openalex.org/W6703351271","https://openalex.org/W6725787379","https://openalex.org/W6734246609"],"related_works":["https://openalex.org/W2410566519","https://openalex.org/W1585155462","https://openalex.org/W2384651879","https://openalex.org/W2517638034","https://openalex.org/W4366725928","https://openalex.org/W4247725880","https://openalex.org/W2249138175","https://openalex.org/W2120097768","https://openalex.org/W2154141294","https://openalex.org/W2978471304"],"abstract_inverted_index":{"The":[0,22,107,123],"paper":[1],"considers":[2],"bimodal":[3,109],"person":[4,138],"identification":[5,16,110,118,139],"problem":[6,140],"by":[7],"analyzing":[8],"the":[9,25,33,37,60,69,90,94,113,129,133,137],"speaker\u2019s":[10],"face":[11,78,100],"and":[12,20,92,99],"voice.":[13],"Two":[14],"speaker":[15,50],"algorithms":[17,135],"are":[18],"developed":[19],"compared.":[21],"idea":[23],"of":[24,29,39,62,71,75,96,102,116,119,125,131],"first":[26],"algorithm":[27],"consists":[28],"extracting":[30],"features":[31],"from":[32,68],"speech":[34,97],"signal":[35],"in":[36,141],"form":[38],"mel":[40],"frequency":[41],"cepstral":[42],"coefficients":[43],"and,":[44],"with":[45,83],"this":[46,126],"basis,":[47],"forming":[48],"a":[49,63,72,80],"model":[51,66],"using":[52],"Gaussian":[53],"mixtures.":[54],"Second":[55],"approach":[56],"is":[57],"based":[58],"on":[59],"use":[61],"universal":[64],"background":[65],"obtained":[67],"records":[70],"large":[73],"number":[74],"speakers.":[76],"For":[77,89],"identification,":[79],"neural":[81],"network":[82],"13":[84],"convolutional":[85],"layers":[86],"was":[87],"used.":[88],"learning":[91],"testing,":[93],"databases":[95],"signals":[98],"images":[101],"100":[103],"people":[104],"were":[105],"formed.":[106],"final":[108],"system":[111],"shows":[112],"high":[114],"level":[115],"accuracy":[117],"more":[120],"than":[121],"95%.":[122],"results":[124],"experiment":[127],"demonstrated":[128],"possibility":[130],"applying":[132],"proposed":[134],"to":[136],"real-life":[142],"systems.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}