{"id":"https://openalex.org/W2889793054","doi":"https://doi.org/10.1109/lsp.2018.2870726","title":"SNR-Invariant Multitask Deep Neural Networks for Robust Speaker Verification","display_name":"SNR-Invariant Multitask Deep Neural Networks for Robust Speaker Verification","publication_year":2018,"publication_date":"2018-09-17","ids":{"openalex":"https://openalex.org/W2889793054","doi":"https://doi.org/10.1109/lsp.2018.2870726","mag":"2889793054"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2870726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2870726","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101853645","display_name":"Qi Yao","orcid":"https://orcid.org/0000-0002-2504-1904"},"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":"Qi Yao","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2504-1904","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":"last","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"],"raw_orcid":"https://orcid.org/0000-0001-8854-3760","affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":3.1121,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93353676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"11","first_page":"1670","last_page":"1674"},"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":0.9991999864578247,"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":0.9922000169754028,"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":0.6257876753807068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5586853623390198},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5336962938308716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5108620524406433},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5103339552879333},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4825855493545532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4690575897693634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4684106707572937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.435702919960022},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.27649855613708496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6257876753807068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5586853623390198},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5336962938308716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5108620524406433},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5103339552879333},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4825855493545532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4690575897693634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4684106707572937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.435702919960022},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27649855613708496},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2018.2870726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2870726","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:ira.lib.polyu.edu.hk:10397/107190","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/107190","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1533861849","https://openalex.org/W1663973292","https://openalex.org/W1916834241","https://openalex.org/W1994244061","https://openalex.org/W2050693797","https://openalex.org/W2095705004","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2143054781","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2180339972","https://openalex.org/W2187089797","https://openalex.org/W2210888091","https://openalex.org/W2397634864","https://openalex.org/W2400341349","https://openalex.org/W2402626018","https://openalex.org/W2405354182","https://openalex.org/W2406312423","https://openalex.org/W2485419308","https://openalex.org/W2594639291","https://openalex.org/W2604209903","https://openalex.org/W2750097321","https://openalex.org/W2786386907","https://openalex.org/W6600284362","https://openalex.org/W6631943919","https://openalex.org/W6712325649","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W2546089952","https://openalex.org/W2090976131","https://openalex.org/W2140022733","https://openalex.org/W1516392727"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,20,83,154],"speaker":[4,152],"verification":[5,191],"is":[6,76,88,129],"to":[7,90,97,114,131,150,189],"achieve":[8],"low":[9],"error":[10],"rates":[11],"under":[12],"noisy":[13,92],"environments.":[14],"We":[15],"observed":[16],"that":[17,118,164,185],"background":[18],"noise":[19],"utterances":[21],"will":[22],"not":[23],"only":[24],"enlarge":[25],"the":[26,36,39,45,50,85,110,116,124,147,155,171,176],"speaker-dependent":[27,100],"<italic":[28,93,105,133,157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[29,94,106,134,158],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i</i>":[30,95,107,135,159],"-vector":[31],"clusters":[32],"but":[33],"also":[34],"shift":[35,42],"clusters,":[37],"with":[38,170],"amount":[40],"of":[41,49,103,182],"depending":[43],"on":[44],"signal-to-noise":[46],"ratio":[47],"(SNR)":[48],"utterances.":[51],"To":[52],"overcome":[53],"this":[54],"SNR-dependent":[55],"clustering":[56],"phenomenon,":[57],"we":[58],"propose":[59],"two":[60,80,166],"deep":[61],"neural":[62],"network":[63,145],"(DNN)":[64],"architectures:":[65],"hierarchical":[66],"regression":[67,81],"DNN":[68,72,87,112,167],"(H-RDNN)":[69],"and":[70,109,139,180,184],"multitask":[71,186],"(MT-DNN).":[73],"The":[74,127,144],"H-RDNN":[75],"formed":[77],"by":[78,123],"stacking":[79],"DNNs":[82],"which":[84],"lower":[86,125],"trained":[89,130],"map":[91],"-vectors":[96,108,136],"their":[98],"respective":[99],"cluster":[101],"means":[102],"clean":[104],"upper":[111],"aims":[113],"regularize":[115],"outliers":[117],"cannot":[119],"be":[120],"denoised":[121,156],"properly":[122],"DNN.":[126],"MT-DNN":[128],"denoise":[132],"(main":[137],"task)":[138],"classify":[140],"speakers":[141],"(auxiliary":[142],"task).":[143],"leverages":[146],"auxiliary":[148],"task":[149],"retain":[151],"information":[153],"-vectors.":[160],"Experimental":[161],"results":[162],"suggest":[163],"these":[165],"architectures":[168],"together":[169],"PLDA":[172,178],"backend":[173],"significantly":[174],"outperform":[175],"multicondition":[177],"model":[179],"mixtures":[181],"PLDA,":[183],"learning":[187],"helps":[188],"boost":[190],"performance.":[192]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}