{"id":"https://openalex.org/W2784332058","doi":"https://doi.org/10.1109/taslp.2018.2791105","title":"DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification","display_name":"DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification","publication_year":2018,"publication_date":"2018-01-08","ids":{"openalex":"https://openalex.org/W2784332058","doi":"https://doi.org/10.1109/taslp.2018.2791105","mag":"2784332058"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2791105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2791105","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":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/77313/1/Tan_Dnn-Based_Score_Calibration.pdf","any_repository_has_fulltext":true},"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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036359785"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.8437,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79511679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":"4","first_page":"700","last_page":"712"},"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":0.996999979019165,"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":0.9868999719619751,"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/calibration","display_name":"Calibration","score":0.716784656047821},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6143664121627808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5919142365455627},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5253400206565857},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5049019455909729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43007373809814453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42541617155075073},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.19728615880012512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14476442337036133},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.12072226405143738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11792987585067749},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10094478726387024}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.716784656047821},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6143664121627808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5919142365455627},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5253400206565857},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5049019455909729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43007373809814453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42541617155075073},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.19728615880012512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14476442337036133},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.12072226405143738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11792987585067749},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10094478726387024},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2791105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2791105","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:10397/77313","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/77313","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/77313/1/Tan_Dnn-Based_Score_Calibration.pdf","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:1783.1-89008","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-89008","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":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/77313","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/77313","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/77313/1/Tan_Dnn-Based_Score_Calibration.pdf","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"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2784332058.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W145476170","https://openalex.org/W620149980","https://openalex.org/W775331923","https://openalex.org/W1486911581","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1545061287","https://openalex.org/W1601717684","https://openalex.org/W1836465849","https://openalex.org/W1916834241","https://openalex.org/W1971758513","https://openalex.org/W1994244061","https://openalex.org/W2025401819","https://openalex.org/W2039057510","https://openalex.org/W2057888214","https://openalex.org/W2100495367","https://openalex.org/W2101587318","https://openalex.org/W2110798204","https://openalex.org/W2116064496","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2143054781","https://openalex.org/W2143694533","https://openalex.org/W2144411866","https://openalex.org/W2145094598","https://openalex.org/W2145846419","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2160306971","https://openalex.org/W2170088868","https://openalex.org/W2180339972","https://openalex.org/W2194775991","https://openalex.org/W2290391586","https://openalex.org/W2395750323","https://openalex.org/W2400341349","https://openalex.org/W2402626018","https://openalex.org/W2405354182","https://openalex.org/W2408608560","https://openalex.org/W2485395001","https://openalex.org/W2485419308","https://openalex.org/W2510637384","https://openalex.org/W2510850125","https://openalex.org/W2587150483","https://openalex.org/W2604209903","https://openalex.org/W2614002621","https://openalex.org/W2749877846","https://openalex.org/W2888441252","https://openalex.org/W2913340405","https://openalex.org/W2962714336","https://openalex.org/W2963936775","https://openalex.org/W2964121744","https://openalex.org/W2997574889","https://openalex.org/W3209042722","https://openalex.org/W4234330420","https://openalex.org/W6605963037","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6640010188","https://openalex.org/W6676481782","https://openalex.org/W6681096077","https://openalex.org/W6712908891","https://openalex.org/W6713524729","https://openalex.org/W6754415462","https://openalex.org/W7065462175"],"related_works":["https://openalex.org/W1994867670","https://openalex.org/W2746471976","https://openalex.org/W2381020483","https://openalex.org/W2893763841","https://openalex.org/W2738707637","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2253551762","https://openalex.org/W2946615417","https://openalex.org/W2778699561"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"and":[3,14,55,61,106],"investigates":[4],"several":[5],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"based":[10],"score":[11,34,53,88,122],"compensation,":[12],"transformation,":[13],"calibration":[15,29,123],"algorithms":[16],"for":[17],"enhancing":[18],"the":[19,32,44,48,52,56,66,80,87,92,113,130,133],"noise":[20],"robustness":[21],"of":[22,40,58,68,109,132],"i-vector":[23,59],"speaker":[24,107],"verification":[25],"systems.":[26],"Unlike":[27],"conventional":[28,134],"methods":[30],"where":[31],"required":[33],"shift":[35],"is":[36,71,97],"a":[37,76],"linear":[38],"function":[39],"SNR":[41],"or":[42],"log-duration,":[43],"DNN":[45,77],"approach":[46],"learns":[47],"complex":[49],"relationship":[50],"between":[51],"shifts":[54],"combination":[57],"pairs":[60],"uncalibrated":[62],"scores.":[63],"Furthermore,":[64],"with":[65],"flexibility":[67],"DNNs,":[69],"it":[70],"possible":[72],"to":[73,78,85,99],"explicitly":[74],"train":[75],"recover":[79],"clean":[81],"scores":[82],"without":[83],"having":[84],"estimate":[86],"shifts.":[89],"To":[90],"alleviate":[91],"overfitting":[93],"problem,":[94],"multitask":[95,126],"learning":[96],"applied":[98],"incorporate":[100],"auxiliary":[101],"information":[102],"such":[103],"as":[104],"SNRs":[105],"ID":[108],"training":[110],"utterances":[111],"into":[112],"DNN.":[114],"Experiments":[115],"on":[116],"NIST":[117],"2012":[118],"SRE":[119],"show":[120],"that":[121],"derived":[124],"from":[125],"DNNs":[127],"can":[128],"improve":[129],"performance":[131],"score-shift":[135],"approch":[136],"significantly,":[137],"especially":[138],"under":[139],"noisy":[140],"conditions.":[141]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
