{"id":"https://openalex.org/W2148091317","doi":"https://doi.org/10.1109/lsp.2014.2323432","title":"Combination of Cepstral and Phonetically Discriminative Features for Speaker Verification","display_name":"Combination of Cepstral and Phonetically Discriminative Features for Speaker Verification","publication_year":2014,"publication_date":"2014-05-13","ids":{"openalex":"https://openalex.org/W2148091317","doi":"https://doi.org/10.1109/lsp.2014.2323432","mag":"2148091317"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2014.2323432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2014.2323432","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01690336/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002627413","display_name":"Achintya Kumar Sarkar","orcid":"https://orcid.org/0000-0002-9870-3980"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Achintya K. Sarkar","raw_affiliation_strings":["LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066876667","display_name":"Cong-Thanh Do","orcid":"https://orcid.org/0000-0003-1748-2846"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cong-Thanh Do","raw_affiliation_strings":["LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044153954","display_name":"Viet-Bac Le","orcid":null},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet-Bac Le","raw_affiliation_strings":["Vocapia Research, Parc Orsay Universit\u00e9, Orsay, France","Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, Parc Orsay Universit\u00e9, Orsay, France","institution_ids":["https://openalex.org/I99555447"]},{"raw_affiliation_string":"Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112867496","display_name":"Claude Barras","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Barras","raw_affiliation_strings":["LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Universit\u00e9 Paris-Sud, Orsay Cedex, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8615,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95981535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"9","first_page":"1040","last_page":"1044"},"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":0.9968000054359436,"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":0.9955000281333923,"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":0.7973331212997437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7388549447059631},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6732126474380493},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.665753960609436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6085456609725952},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5878171920776367},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.581597626209259},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5718830823898315},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.564558744430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5589651465415955},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5265194177627563},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5117818713188171},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5107629299163818},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.500175952911377},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.41730231046676636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15160036087036133}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7973331212997437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388549447059631},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6732126474380493},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.665753960609436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6085456609725952},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5878171920776367},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.581597626209259},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5718830823898315},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.564558744430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5589651465415955},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5265194177627563},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5117818713188171},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5107629299163818},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.500175952911377},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.41730231046676636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15160036087036133},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2014.2323432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2014.2323432","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01690336v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01690336","pdf_url":"https://hal.science/hal-01690336/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters, 2014, 21 (9), pp.1040 - 1044. ⟨10.1109/LSP.2014.2323432⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01690336v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01690336","pdf_url":"https://hal.science/hal-01690336/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters, 2014, 21 (9), pp.1040 - 1044. ⟨10.1109/LSP.2014.2323432⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2148091317.pdf","grobid_xml":"https://content.openalex.org/works/W2148091317.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W26772505","https://openalex.org/W128628490","https://openalex.org/W132821814","https://openalex.org/W160722039","https://openalex.org/W177307080","https://openalex.org/W197151588","https://openalex.org/W1553271421","https://openalex.org/W1569592550","https://openalex.org/W1594707156","https://openalex.org/W2041823554","https://openalex.org/W2071489795","https://openalex.org/W2090861223","https://openalex.org/W2102264166","https://openalex.org/W2107831318","https://openalex.org/W2114851258","https://openalex.org/W2134689131","https://openalex.org/W2135346934","https://openalex.org/W2138547132","https://openalex.org/W2143486266","https://openalex.org/W2146871184","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2158489828","https://openalex.org/W2159948109","https://openalex.org/W2162273278","https://openalex.org/W2165712214","https://openalex.org/W2293234034","https://openalex.org/W2295914911","https://openalex.org/W2401027203","https://openalex.org/W3145164839","https://openalex.org/W4246070010","https://openalex.org/W4298164478","https://openalex.org/W6605273041","https://openalex.org/W6633911496","https://openalex.org/W6635733711","https://openalex.org/W6676245417","https://openalex.org/W6679986405"],"related_works":["https://openalex.org/W2888091758","https://openalex.org/W4382052966","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W1963976507","https://openalex.org/W106160982","https://openalex.org/W2359140082"],"abstract_inverted_index":{"Most":[0],"speaker":[1,50,71,146],"recognition":[2,72],"systems":[3],"rely":[4],"on":[5,29,76,86,100],"short-term":[6,128],"acoustic":[7],"cepstral":[8,54,129,166],"features":[9,119],"for":[10],"extracting":[11],"the":[12,16,49,84,115,127,145,160],"speaker-relevant":[13],"information":[14,38,122],"from":[15],"signal.":[17],"But":[18],"phonetic":[19],"discriminant":[20,56],"features,":[21,55,57],"extracted":[22],"by":[23,64],"a":[24,36,59,65,87,101],"bottle-neck":[25],"multi-layer":[26],"perceptron":[27],"(MLP)":[28],"longer":[30],"stretches":[31],"of":[32,61,104],"time,":[33],"can":[34],"provide":[35],"complementary":[37,125],"and":[39,58,83,108,140,144],"have":[40],"been":[41],"adopted":[42],"in":[43],"speech":[44],"transcription":[45],"systems.":[46],"We":[47,68],"compare":[48],"verification":[51,147],"performance":[52,132],"using":[53,164],"concatenation":[60],"both":[62,137],"followed":[63],"dimension":[66],"reduction.":[67],"consider":[69],"two":[70,92],"systems,":[73],"one":[74],"based":[75],"maximum":[77],"likelihood":[78],"linear":[79],"regression":[80],"(MLLR)":[81],"super-vectors":[82],"other":[85],"state-of-the-art":[88],"i-vector":[89,162],"system":[90,163],"with":[91,136],"session":[93],"variability":[94],"compensation":[95],"schemes.":[96],"Experiments":[97],"are":[98],"reported":[99],"standard":[102],"configuration":[103],"NIST":[105],"SRE":[106],"2008":[107],"2010":[109],"databases.":[110],"The":[111,131],"results":[112],"show":[113],"that":[114],"phonetically":[116],"discriminative":[117],"MLP":[118],"retain":[120],"speaker-specific":[121],"which":[123],"is":[124,134,152],"to":[126,155,159],"features.":[130,167],"improvement":[133],"obtained":[135],"score":[138],"domain":[139,142],"feature":[141],"fusion":[143],"equal":[148],"error":[149],"rate":[150],"(EER)":[151],"reduced":[153],"up":[154],"50%":[156],"relative,":[157],"compared":[158],"best":[161],"only":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-06-24T00:00:00"}