{"id":"https://openalex.org/W2783108448","doi":"https://doi.org/10.1109/taslp.2018.2793670","title":"Generalizing I-Vector Estimation for Rapid Speaker Recognition","display_name":"Generalizing I-Vector Estimation for Rapid Speaker Recognition","publication_year":2018,"publication_date":"2018-01-15","ids":{"openalex":"https://openalex.org/W2783108448","doi":"https://doi.org/10.1109/taslp.2018.2793670","mag":"2783108448"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2793670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2793670","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/A5045048913","display_name":"Longting Xu","orcid":"https://orcid.org/0000-0002-2329-895X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Longting Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Institute for Infocomm Research, Singapore","Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2329-895X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["JP","SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Data Science Research Laboratories, NEC Corporation, Tokyo, Japan","Human Language Technology Department, Institute for Infocomm Research, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9133-3000","affiliations":[{"raw_affiliation_string":"Data Science Research Laboratories, NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047980942","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-4400-3823"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.9648,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92554582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"4","first_page":"749","last_page":"759"},"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":0.9975000023841858,"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":0.992900013923645,"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":0.6682238578796387},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5838238000869751},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5188866257667542},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5137585401535034},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5091642737388611},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5071842670440674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4825015068054199},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.45990630984306335},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4444291293621063},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43813174962997437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.358609676361084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33966588973999023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2652941346168518},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16523081064224243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682238578796387},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5838238000869751},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5188866257667542},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5137585401535034},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5091642737388611},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5071842670440674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4825015068054199},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.45990630984306335},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4444291293621063},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43813174962997437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.358609676361084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33966588973999023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2652941346168518},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16523081064224243},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2793670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2793670","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5517341317","display_name":"\u57fa\u4e8e\u975e\u6b63\u4ea4\u591a\u5740\u7684\u8ba4\u77e5\u65e0\u7ebf\u7f51\u63a5\u5165\u6280\u672f\u7814\u7a76","funder_award_id":"61671252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W1483851010","https://openalex.org/W1506806321","https://openalex.org/W1943391042","https://openalex.org/W1970931527","https://openalex.org/W2017554292","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2064364374","https://openalex.org/W2075581860","https://openalex.org/W2078169166","https://openalex.org/W2119468495","https://openalex.org/W2121415728","https://openalex.org/W2121812409","https://openalex.org/W2127672898","https://openalex.org/W2141083997","https://openalex.org/W2145384363","https://openalex.org/W2146635662","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2183016404","https://openalex.org/W2230477019","https://openalex.org/W2280397712","https://openalex.org/W2395750323","https://openalex.org/W2397336997","https://openalex.org/W2404282455","https://openalex.org/W2404874347","https://openalex.org/W2406312423","https://openalex.org/W2407024733","https://openalex.org/W2471556897","https://openalex.org/W2478270136","https://openalex.org/W2479269803","https://openalex.org/W2595142274","https://openalex.org/W2749976445","https://openalex.org/W2963068250","https://openalex.org/W4212863985","https://openalex.org/W6628943792","https://openalex.org/W6713195658","https://openalex.org/W6713414053","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2886934452","https://openalex.org/W1489099099","https://openalex.org/W2024369332"],"abstract_inverted_index":{"An":[0],"i-vector":[1,41,56,99,123,165,189],"is":[2,30,118],"a":[3,16,95],"compact":[4],"representation":[5,35],"that":[6,177],"captures":[7],"both":[8],"the":[9,20,32,49,65,71,81,102,106,113,122,131,141,147,153,160,170,178,187],"speaker":[10,38],"and":[11,29],"session":[12],"variabilities":[13],"rendered":[14],"in":[15,57,125,136,164],"spoken":[17],"utterance.":[18],"Over":[19],"past":[21],"years,":[22],"it":[23],"has":[24],"prevailed":[25],"over":[26,140,186],"other":[27],"techniques":[28],"now":[31],"de":[33],"facto":[34],"for":[36],"text-independent":[37],"recognition.":[39],"Standard":[40],"extraction":[42,100,115],"requires":[43],"intense":[44,61],"computation":[45,50,62,82],"at":[46],"run-time.":[47],"Reducing":[48],"will":[51],"allow":[52],"effective":[53],"use":[54,132],"of":[55,83,133,146,173],"more":[58],"applications.":[59],"Such":[60],"arises":[63],"from":[64],"posterior":[66,84,108],"covariance":[67,85,109],"matrix,":[68],"when":[69],"estimating":[70],"i-vector.":[72],"There":[73],"have":[74],"been":[75],"studies":[76],"on":[77,169],"how":[78],"to":[79,98,104,158],"simplify":[80],"matrix":[86],"with":[87,138,190],"modest":[88],"success.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93,129,151],"propose":[94],"novel":[96],"approach":[97,182],"without":[101],"need":[103],"evaluate":[105],"full":[107],"thereby":[110],"speeding":[111],"up":[112],"run-time":[114],"process.":[116],"This":[117],"achieved":[119],"by":[120],"generalizing":[121],"estimation":[124],"two":[126],"ways.":[127],"First,":[128],"introduce":[130,152],"occupancy":[134],"reweighting":[135],"conjunction":[137],"whitening":[139],"Baum-Welch":[142],"statistics":[143],"as":[144],"part":[145],"preprocessing":[148],"step.":[149],"Second,":[150],"so-called":[154],"subspace-orthogonalizing":[155],"prior":[156,163],"(SOP)":[157],"replace":[159],"standard":[161,188],"Gaussian":[162],"formulation.":[166],"Experiments":[167],"conducted":[168],"extended-core":[171],"task":[172],"NIST":[174],"SRE'10":[175],"show":[176],"proposed":[179],"rapid":[180],"SOP":[181],"achieves":[183],"considerable":[184],"speed-up":[185],"comparable":[191],"equal":[192],"error":[193],"rates.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}