{"id":"https://openalex.org/W3205932228","doi":"https://doi.org/10.1109/lsp.2021.3122796","title":"Optimizing Multi-Taper Features for Deep Speaker Verification","display_name":"Optimizing Multi-Taper Features for Deep Speaker Verification","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3205932228","doi":"https://doi.org/10.1109/lsp.2021.3122796","mag":"3205932228"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3122796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3122796","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.10983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014303571","display_name":"Xuechen Liu","orcid":"https://orcid.org/0000-0003-1207-5651"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FI","FR"],"is_corresponding":true,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["Inria Centre de Recherche Nancy Grand Est, 202553 Villers-ls-Nancy, France, 54600 (e-mail: xuecliu@uef.fi)","Speech Modeling for Facilitating Oral-Based Communication","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"Inria Centre de Recherche Nancy Grand Est, 202553 Villers-ls-Nancy, France, 54600 (e-mail: xuecliu@uef.fi)","institution_ids":["https://openalex.org/I4210127166"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Md Sahidullah","raw_affiliation_strings":["MULTISPEECH, Inria, Nancy, Lorraine, France, 54000 (e-mail: sahidullahmd@gmail.com)","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH, Inria, Nancy, Lorraine, France, 54000 (e-mail: sahidullahmd@gmail.com)","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland, Finland, FI-80101 (e-mail: tomi.kinnunen@uef.fi)","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland, Finland, FI-80101 (e-mail: tomi.kinnunen@uef.fi)","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014303571"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997","https://openalex.org/I4210127166"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70017036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"28","issue":null,"first_page":"2187","last_page":"2191"},"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":0.9988999962806702,"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":0.9846000075340271,"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":0.7790462970733643},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7335178256034851},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6716413497924805},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6495258808135986},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6004379987716675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5710309147834778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5087981820106506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053832530975342},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4944274425506592},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4766210615634918},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4706629514694214},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4622397720813751},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44958120584487915},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4460830092430115},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4347842335700989},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39321550726890564},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39243370294570923},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35342493653297424},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14608246088027954},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10366407036781311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790462970733643},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7335178256034851},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6716413497924805},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6495258808135986},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6004379987716675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5710309147834778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5087981820106506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053832530975342},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4944274425506592},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4766210615634918},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4706629514694214},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4622397720813751},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44958120584487915},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4460830092430115},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4347842335700989},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39321550726890564},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39243370294570923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35342493653297424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14608246088027954},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10366407036781311},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":3,"locations":[{"id":"doi:10.1109/lsp.2021.3122796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3122796","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:arXiv.org:2110.10983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.10983","pdf_url":"https://arxiv.org/pdf/2110.10983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03394152v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03394152","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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, 2021, 28, pp.2187 - 2191. ⟨10.1109/LSP.2021.3122796⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.10983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.10983","pdf_url":"https://arxiv.org/pdf/2110.10983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G598299161","display_name":null,"funder_award_id":"309629","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1493982694","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1578856370","https://openalex.org/W1665214252","https://openalex.org/W1936725236","https://openalex.org/W1977331234","https://openalex.org/W2028124797","https://openalex.org/W2062003163","https://openalex.org/W2111460811","https://openalex.org/W2131475987","https://openalex.org/W2137075158","https://openalex.org/W2155722796","https://openalex.org/W2170088868","https://openalex.org/W2222372807","https://openalex.org/W2402146185","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2770454110","https://openalex.org/W2794506738","https://openalex.org/W2802488037","https://openalex.org/W2808631503","https://openalex.org/W2887814324","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2947256846","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3046380034","https://openalex.org/W3128666957","https://openalex.org/W3129570578","https://openalex.org/W3131786367","https://openalex.org/W3137249133","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6637242042","https://openalex.org/W6689127821","https://openalex.org/W6740167877"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2543208657","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W66821593"],"abstract_inverted_index":{"Multi-taper":[0],"estimators":[1],"provide":[2],"low-variance":[3],"power":[4],"spectrum":[5],"estimates":[6],"that":[7],"can":[8],"be":[9],"used":[10],"in":[11,92],"place":[12],"of":[13,49,61,90,94,108],"the":[14,47,69,87,99],"windowed":[15],"discrete":[16],"Fourier":[17],"transform":[18],"(DFT)":[19],"to":[20,67],"extract":[21],"speech":[22],"features":[23],"such":[24],"as":[25],"mel-frequency":[26],"cepstral":[27],"coefficients":[28],"(MFCCs).":[29],"Even":[30],"if":[31],"past":[32],"work":[33],"has":[34],"reported":[35],"promising":[36],"automatic":[37],"speaker":[38],"verification":[39],"(ASV)":[40],"results":[41],"with":[42,52,73],"Gaussian":[43],"mixture":[44],"model-based":[45],"classifiers,":[46],"performance":[48],"multi-taper":[50,70],"MFCCs":[51],"deep":[53,75],"ASV":[54,80],"systems":[55],"remains":[56],"an":[57],"open":[58],"question.":[59],"Instead":[60],"a":[62,74,83,105],"static-taper":[63],"design,":[64],"we":[65],"propose":[66],"optimize":[68],"estimator":[71],"jointly":[72],"neural":[76],"network":[77],"trained":[78],"for":[79],"tasks.":[81],"With":[82],"maximum":[84],"improvement":[85],"on":[86],"SITW":[88],"corpus":[89],"25.8%":[91],"terms":[93],"equal":[95],"error":[96],"rate":[97],"over":[98],"static-taper,":[100],"our":[101],"method":[102],"helps":[103],"preserve":[104],"balanced":[106],"level":[107],"leakage":[109],"and":[110],"variance,":[111],"providing":[112],"more":[113],"robustness.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}