{"id":"https://openalex.org/W2749877846","doi":"https://doi.org/10.21437/interspeech.2017-656","title":"i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification","display_name":"i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2749877846","doi":"https://doi.org/10.21437/interspeech.2017-656","mag":"2749877846"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106995/1/tan17_interspeech.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":["The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","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":["The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036359785"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77340351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1562","last_page":"1566"},"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":0.9980000257492065,"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/speaker-verification","display_name":"Speaker verification","score":0.7530921101570129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455850839614868},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6811356544494629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6555854082107544},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6091445684432983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500216007232666},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4910888671875},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47432252764701843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4511496424674988},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44124481081962585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13248780369758606},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1134347915649414},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05478969216346741}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7530921101570129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455850839614868},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6811356544494629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6555854082107544},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6091445684432983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500216007232666},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4910888671875},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47432252764701843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4511496424674988},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44124481081962585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13248780369758606},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1134347915649414},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05478969216346741},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/106995","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/106995","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106995/1/tan17_interspeech.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":"Conference Paper"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/77241","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/77241","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":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/106995","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/106995","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106995/1/tan17_interspeech.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":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2749877846.pdf","grobid_xml":"https://content.openalex.org/works/W2749877846.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W620149980","https://openalex.org/W775331923","https://openalex.org/W1545061287","https://openalex.org/W1916834241","https://openalex.org/W1994244061","https://openalex.org/W2025401819","https://openalex.org/W2057888214","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/W2145846419","https://openalex.org/W2150769028","https://openalex.org/W2170088868","https://openalex.org/W2175575774","https://openalex.org/W2180339972","https://openalex.org/W2395750323","https://openalex.org/W2400341349","https://openalex.org/W2402626018","https://openalex.org/W2405354182","https://openalex.org/W2406312423","https://openalex.org/W2408608560","https://openalex.org/W2485395001","https://openalex.org/W2485419308","https://openalex.org/W2510637384","https://openalex.org/W2510850125","https://openalex.org/W2604209903","https://openalex.org/W2614002621","https://openalex.org/W2784332058","https://openalex.org/W2888441252","https://openalex.org/W2997574889","https://openalex.org/W3209042722"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"applying":[3],"multi-task":[4],"learning":[5],"to":[6,28,55,93,109],"train":[7],"deep":[8],"neural":[9],"networks":[10],"(DNNs)":[11],"for":[12,90],"calibrating":[13],"the":[14,26,30,40,56,65,72,85,91,95,101,110,115,120,126],"PLDA":[15,66,103,127],"scores":[16,104],"of":[17,42,63],"speaker":[18,58],"verification":[19],"systems":[20],"under":[21],"noisy":[22],"environments.":[23],"To":[24],"facilitate":[25],"DNNs":[27,92,116],"learn":[29,94],"main":[31,96],"task":[32,98],"(calibration),":[33],"several":[34],"auxiliary":[35,86],"tasks":[36,87],"were":[37],"introduced,":[38],"including":[39],"prediction":[41],"SNR":[43],"and":[44,48,99],"duration":[45],"from":[46],"i-vectors":[47],"classifying":[49],"whether":[50],"an":[51,106],"i-vector":[52],"pair":[53],"belongs":[54],"same":[57],"or":[59],"not.":[60],"The":[61],"possibility":[62],"replacing":[64],"model":[67,128],"by":[68],"a":[69],"DNN":[70],"during":[71],"scoring":[73],"stage":[74],"is":[75,129],"also":[76],"explored.":[77],"Evaluations":[78],"on":[79],"noise":[80],"contaminated":[81],"speech":[82],"suggest":[83],"that":[84,100,125],"are":[88,105],"important":[89],"calibration":[97],"uncalibrated":[102],"essential":[107],"input":[108],"DNNs.":[111],"Without":[112],"this":[113],"input,":[114],"can":[117],"only":[118],"predict":[119],"score":[121],"shifts":[122],"accurately,":[123],"suggesting":[124],"indispensable.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}