{"id":"https://openalex.org/W2129066450","doi":"https://doi.org/10.1109/icassp.2012.6288858","title":"Towards noise-robust speaker recognition using probabilistic linear discriminant analysis","display_name":"Towards noise-robust speaker recognition using probabilistic linear discriminant analysis","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2129066450","doi":"https://doi.org/10.1109/icassp.2012.6288858","mag":"2129066450"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/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, Inc., USA","SRI International, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International, USA#TAB#","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"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":"Lukas Burget","raw_affiliation_strings":["SRI International, Inc., USA","SRI International, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International, USA#TAB#","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"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":"Luciana Ferrer","raw_affiliation_strings":["SRI International, Inc., USA","SRI International, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International, USA#TAB#","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","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":"Martin Graciarena","raw_affiliation_strings":["SRI International, Inc., USA","SRI International, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International, USA#TAB#","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","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":"Nicolas Scheffer","raw_affiliation_strings":["SRI International, Inc., USA","SRI International, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International, USA#TAB#","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4253","last_page":"4256"},"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":0.9983000159263611,"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":0.9789000153541565,"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/nist","display_name":"NIST","score":0.7076509594917297},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.7010555267333984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984686255455017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.665233850479126},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6083446145057678},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5893307328224182},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5625752806663513},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5521687865257263},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4803832173347473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4766331911087036},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4634001553058624},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45421919226646423},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.453625351190567},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4433947205543518},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42921721935272217},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1971152424812317}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7076509594917297},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.7010555267333984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984686255455017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.665233850479126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6083446145057678},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5893307328224182},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5625752806663513},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5521687865257263},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4803832173347473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4766331911087036},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4634001553058624},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45421919226646423},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.453625351190567},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4433947205543518},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42921721935272217},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1971152424812317},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.5165","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.5165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/lei_icassp2012_0004253.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2026809232","https://openalex.org/W2095965719","https://openalex.org/W2101684547","https://openalex.org/W2102346872","https://openalex.org/W2121812409","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2164432048","https://openalex.org/W2395750323","https://openalex.org/W2396983800","https://openalex.org/W2406312423","https://openalex.org/W6675700563","https://openalex.org/W6680375658","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2118039276","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"This":[0],"work":[1],"addresses":[2],"the":[3,14,22,38,65,90],"problem":[4],"of":[5,130],"speaker":[6,42],"verification":[7,43],"where":[8],"additive":[9],"noise":[10,79],"is":[11,45,118],"present":[12,123],"in":[13,89,105],"enrollment":[15],"and":[16,56,69,76,140],"testing":[17],"utterances.":[18],"We":[19,34,54,81,113],"show":[20,83],"how":[21,84],"current":[23,91],"state-of-the-art":[24],"framework":[25],"can":[26,101],"be":[27],"effectively":[28],"used":[29],"to":[30,47],"mitigate":[31],"this":[32,116],"effect.":[33],"first":[35],"look":[36],"at":[37,107],"degradation":[39],"a":[40,58],"standard":[41,132],"system":[44],"subjected":[46],"when":[48],"presented":[49],"with":[50,60],"noisy":[51,61,86],"speech":[52],"waveforms.":[53],"designed":[55],"generated":[57],"corpus":[59],"conditions,":[62],"based":[63],"on":[64],"NIST":[66],"SRE":[67],"2008":[68],"2010":[70],"data,":[71],"built":[72],"using":[73],"open-source":[74],"tools":[75],"freely":[77],"available":[78],"samples.":[80],"then":[82],"adding":[85],"training":[87],"data":[88],"i-vector-based":[92],"approach":[93],"followed":[94],"by":[95],"probabilistic":[96],"linear":[97,143],"discriminant":[98],"analysis":[99],"(PLDA)":[100],"bring":[102],"significant":[103],"gains":[104],"accuracy":[106],"various":[108],"signal-to-noise":[109],"ratio":[110],"(SNR)":[111],"levels.":[112],"demonstrate":[114],"that":[115],"improvement":[117],"not":[119],"feature-specific":[120],"as":[121],"we":[122],"positive":[124],"results":[125],"for":[126],"three":[127],"disparate":[128],"sets":[129],"features:":[131],"mel":[133],"frequency":[134],"cepstral":[135],"coefficients,":[136],"prosodic":[137],"polynomial":[138],"co-efficients":[139],"maximum":[141],"likelihood":[142],"regression":[144],"(MLLR)":[145],"transforms.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}