{"id":"https://openalex.org/W2786386907","doi":"https://doi.org/10.1109/taslp.2018.2796843","title":"Denoised Senone I-Vectors for Robust Speaker Verification","display_name":"Denoised Senone I-Vectors for Robust Speaker Verification","publication_year":2018,"publication_date":"2018-01-25","ids":{"openalex":"https://openalex.org/W2786386907","doi":"https://doi.org/10.1109/taslp.2018.2796843","mag":"2786386907"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2796843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2796843","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5036359785","display_name":"Zhili Tan","orcid":"https://orcid.org/0000-0002-2445-5240"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhili Tan","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Kan-Wing Mak","raw_affiliation_strings":["Department of Computer Science, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064702198","display_name":"Yingke Zhu","orcid":"https://orcid.org/0000-0002-9370-6082"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yingke Zhu","raw_affiliation_strings":["Department of Computer Science, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036359785"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":3.7124,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94381472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":"4","first_page":"820","last_page":"830"},"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":0.9983999729156494,"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":0.9919999837875366,"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/autoencoder","display_name":"Autoencoder","score":0.7986582517623901},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7356425523757935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7156145572662354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6250241994857788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5982152223587036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.539340078830719},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4809260070323944},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4801175594329834},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.4621271789073944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45269566774368286}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7986582517623901},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7356425523757935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156145572662354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6250241994857788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982152223587036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.539340078830719},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4809260070323944},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4801175594329834},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4621271789073944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45269566774368286}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2796843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2796843","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/77467","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/77467","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Journal/Magazine Article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-89009","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-89009","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1994244061","https://openalex.org/W2008557021","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2062826588","https://openalex.org/W2078169166","https://openalex.org/W2101587318","https://openalex.org/W2110798204","https://openalex.org/W2116064496","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2136922672","https://openalex.org/W2143054781","https://openalex.org/W2143694533","https://openalex.org/W2145094598","https://openalex.org/W2145846419","https://openalex.org/W2147147599","https://openalex.org/W2148091317","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2170088868","https://openalex.org/W2175575774","https://openalex.org/W2180339972","https://openalex.org/W2198724430","https://openalex.org/W2268629890","https://openalex.org/W2290391586","https://openalex.org/W2327501763","https://openalex.org/W2396144419","https://openalex.org/W2397236868","https://openalex.org/W2397346386","https://openalex.org/W2400341349","https://openalex.org/W2400388989","https://openalex.org/W2402626018","https://openalex.org/W2403265407","https://openalex.org/W2405354182","https://openalex.org/W2405505124","https://openalex.org/W2405950182","https://openalex.org/W2485419308","https://openalex.org/W2546853769","https://openalex.org/W2566925314","https://openalex.org/W2592513362","https://openalex.org/W2604209903","https://openalex.org/W2608712415","https://openalex.org/W2614002621","https://openalex.org/W2636483419","https://openalex.org/W2746742816","https://openalex.org/W2749877846","https://openalex.org/W2997574889","https://openalex.org/W3123535731","https://openalex.org/W4234330420","https://openalex.org/W6608353291","https://openalex.org/W6676481782","https://openalex.org/W6681096077","https://openalex.org/W6712282327","https://openalex.org/W6712620166","https://openalex.org/W6712908891","https://openalex.org/W6713137374","https://openalex.org/W6713380023","https://openalex.org/W6713383670","https://openalex.org/W7065462175"],"related_works":["https://openalex.org/W4287995534","https://openalex.org/W2998168123","https://openalex.org/W2404514746","https://openalex.org/W2743258233","https://openalex.org/W2772780115","https://openalex.org/W2311479510","https://openalex.org/W2806866760","https://openalex.org/W2586441539","https://openalex.org/W1905704307","https://openalex.org/W1835905048"],"abstract_inverted_index":{"Recently,":[0],"it":[1,67],"has":[2],"been":[3],"shown":[4],"that":[5,59,151,171,183,193],"senone":[6,13,36,62,78,129,143,152,181,187,204],"i-vectors,":[7],"whose":[8],"posteriors":[9,79,130],"are":[10,164],"produced":[11],"by":[12,81,93],"deep":[14,90,96],"neural":[15,116],"networks":[16],"(DNNs),":[17],"outperform":[18,154,184],"the":[19,40,43,50,72,82,109,120,137,155,161,185],"conventional":[20,156,186],"Gaussian":[21],"mixture":[22],"model":[23],"(GMM)":[24],"i-vectors":[25,37,63,139,153,182],"in":[26,64],"both":[27],"speaker":[28,176],"and":[29,77,128],"language":[30],"recognition":[31],"tasks.":[32],"The":[33],"success":[34],"of":[35,42,101,122],"relies":[38],"on":[39,99,146],"capability":[41],"DNN":[44],"to":[45,60,70,112,136,178,199],"incorporate":[46],"phonetic":[47],"information":[48,177],"into":[49],"i-vector":[51,132],"extraction":[52,121,202],"process.":[53],"In":[54],"this":[55,85],"paper,":[56],"we":[57,87],"argue":[58],"apply":[61],"noisy":[65],"environments,":[66],"is":[68,196],"important":[69],"robustify":[71],"phonetically":[73,167],"discriminative":[74],"acoustic":[75],"features":[76,127,163],"estimated":[80],"DNN.":[83],"To":[84],"end,":[86],"propose":[88],"a":[89,95,102],"architecture":[91],"formed":[92],"stacking":[94],"belief":[97],"network":[98,117],"top":[100],"denoising":[103,114],"autoencoder":[104],"(DAE).":[105],"After":[106],"backpropagation":[107],"fine-tuning,":[108],"network,":[110],"referred":[111],"as":[113,140],"autoencoder-deep":[115],"(DAE-DNN),":[118],"facilitates":[119],"robust":[123],"phonetically-discriminitive":[124],"bottleneck":[125],"(BN)":[126],"for":[131],"extraction.":[133],"We":[134],"refer":[135],"resulting":[138],"denoised":[141],"BN-based":[142,180],"i-vectors.":[144,158,188],"Results":[145],"NIST":[147],"2012":[148],"SRE":[149],"show":[150],"GMM":[157],"More":[159],"interestingly,":[160],"BN":[162,200],"not":[165],"only":[166],"discriminative,":[168],"results":[169],"suggest":[170],"they":[172],"also":[173,191],"contain":[174],"sufficient":[175],"produce":[179],"This":[189],"work":[190],"shows":[192],"DAE":[194],"training":[195],"more":[197],"beneficial":[198],"feature":[201],"than":[203],"posterior":[205],"estimation.":[206]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}