{"id":"https://openalex.org/W1528954144","doi":"https://doi.org/10.1109/icassp.2015.7178885","title":"Advances in deep neural network approaches to speaker recognition","display_name":"Advances in deep neural network approaches to speaker recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1528954144","doi":"https://doi.org/10.1109/icassp.2015.7178885","mag":"1528954144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","[Speech Technology and Research Laboratory, SRI International, California, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, California, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","[Speech Technology and Research Laboratory, SRI International, California, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, California, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Departamento de Computaci6n, Universidad de Buenos Aires and CONICET, Argentina","Departamento de Computaci\u00f3n, FCEN, Universidad de Buenos Aires and CONICET, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Computaci6n, Universidad de Buenos Aires and CONICET, Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]},{"raw_affiliation_string":"Departamento de Computaci\u00f3n, FCEN, Universidad de Buenos Aires and CONICET, Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4814","last_page":"4818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/speech-recognition","display_name":"Speech recognition","score":0.800838053226471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7713969349861145},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7306458353996277},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.666421115398407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6375565528869629},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6321852207183838},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6096069812774658},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49420955777168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49345365166664124},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4783022999763489},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4287268817424774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4215204417705536},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41242825984954834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0976572334766388}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.800838053226471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713969349861145},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7306458353996277},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.666421115398407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6375565528869629},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6321852207183838},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6096069812774658},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49420955777168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49345365166664124},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4783022999763489},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4287268817424774},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4215204417705536},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41242825984954834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0976572334766388},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W651157033","https://openalex.org/W1512214071","https://openalex.org/W2039057510","https://openalex.org/W2043994950","https://openalex.org/W2121812409","https://openalex.org/W2129066450","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2158069733","https://openalex.org/W2175575774","https://openalex.org/W2183984815","https://openalex.org/W2185814970","https://openalex.org/W2295880672","https://openalex.org/W2296295429","https://openalex.org/W2397474108","https://openalex.org/W2397634864","https://openalex.org/W2405476549","https://openalex.org/W6621565597","https://openalex.org/W6685355283","https://openalex.org/W6686687092","https://openalex.org/W6697225806","https://openalex.org/W6697494326","https://openalex.org/W6712325649","https://openalex.org/W6712467859","https://openalex.org/W6713590052"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2148323604","https://openalex.org/W2181956362","https://openalex.org/W2556771176"],"abstract_inverted_index":{"The":[0,81],"recent":[1],"application":[2],"of":[3,85,116,127,136,164],"deep":[4],"neural":[5],"networks":[6],"(DNN)":[7],"to":[8,42,50,129,143,148],"speaker":[9,120],"identification":[10],"(SID)":[11],"has":[12],"resulted":[13],"in":[14,31,69,161],"significant":[15],"improvements":[16],"over":[17],"current":[18],"state-of-the-art":[19],"on":[20,35,112],"telephone":[21],"speech.":[22,37,150],"In":[23],"this":[24],"work,":[25],"we":[26],"report":[27],"a":[28,79,90,100,125],"similar":[29],"achievement":[30],"DNN-based":[32,43,156],"SID":[33],"performance":[34],"microphone":[36,130,149],"We":[38],"consider":[39],"two":[40],"approaches":[41],"SID:":[44],"one":[45],"that":[46,55],"uses":[47,56],"the":[48,57,66,71,113,117,155,162],"DNN":[49,58,91,137],"extract":[51],"features,":[52],"and":[53,169],"another":[54],"during":[59],"feature":[60,138],"modeling.":[61],"Modeling":[62],"is":[63,76,92,132],"conducted":[64],"using":[65],"DNN/i-vector":[67],"framework,":[68],"which":[70],"traditional":[72],"universal":[73,102],"background":[74,103],"model":[75,104,108],"replaced":[77],"with":[78,99],"DNN.":[80],"recently":[82],"proposed":[83],"use":[84],"bottleneck":[86],"features":[87],"extracted":[88],"from":[89],"also":[93,159],"evaluated.":[94],"Systems":[95],"are":[96,140,158],"first":[97],"compared":[98],"conventional":[101],"(UBM)":[105],"Gaussian":[106],"mixture":[107],"(GMM)":[109],"i-vector":[110],"system":[111],"clean":[114],"conditions":[115],"NIST":[118],"2012":[119],"recognition":[121],"evaluation":[122],"corpus,":[123],"where":[124],"lack":[126],"robustness":[128,147],"speech":[131],"found.":[133],"Several":[134],"methods":[135],"processing":[139],"then":[141],"applied":[142],"bring":[144],"significantly":[145],"greater":[146],"To":[151],"direct":[152],"future":[153],"research,":[154],"systems":[157],"evaluated":[160],"context":[163],"audio":[165],"degradations":[166],"including":[167],"noise":[168],"reverberation.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":16},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}