{"id":"https://openalex.org/W2059529407","doi":"https://doi.org/10.1109/tasl.2013.2253096","title":"A Symmetric Kernel Partial Least Squares Framework for Speaker Recognition","display_name":"A Symmetric Kernel Partial Least Squares Framework for Speaker Recognition","publication_year":2013,"publication_date":"2013-03-15","ids":{"openalex":"https://openalex.org/W2059529407","doi":"https://doi.org/10.1109/tasl.2013.2253096","mag":"2059529407"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2253096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2253096","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 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/A5059650977","display_name":"B. Srinivasan","orcid":"https://orcid.org/0000-0002-3118-5779"},"institutions":[{"id":"https://openalex.org/I53465836","display_name":"Bangalore University","ror":"https://ror.org/050j2vm64","country_code":"IN","type":"education","lineage":["https://openalex.org/I53465836"]},{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"B. V. Srinivasan","raw_affiliation_strings":["Adobe Research Bangalore Laboratories, Bangalore, India","[Adobe Research Bangalore Laboratories, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Adobe Research Bangalore Laboratories, Bangalore, India","institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I53465836"]},{"raw_affiliation_string":"[Adobe Research Bangalore Laboratories, Bangalore, India]","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110114643","display_name":"Yuancheng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuancheng Luo","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Garcia-Romero","raw_affiliation_strings":["Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence (HLTCOE), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056837482","display_name":"Dmitry N. Zotkin","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. N. Zotkin","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Duraiswami","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA#TAB#","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059650977"],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I53465836"],"apc_list":null,"apc_paid":null,"fwci":3.8472,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93546918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"7","first_page":"1415","last_page":"1423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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":0.9685999751091003,"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/discriminative-model","display_name":"Discriminative model","score":0.6802910566329956},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6789519190788269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6624911427497864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6179209351539612},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6002364158630371},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5905730724334717},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.581403374671936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811194777488708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5438556671142578},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.4878549575805664},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4576112627983093},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4428193271160126},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.42222264409065247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23488447070121765}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6802910566329956},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6789519190788269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624911427497864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6179209351539612},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6002364158630371},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5905730724334717},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.581403374671936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811194777488708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5438556671142578},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.4878549575805664},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4576112627983093},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4428193271160126},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.42222264409065247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23488447070121765},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2253096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2253096","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W1535298460","https://openalex.org/W1601795611","https://openalex.org/W1993482042","https://openalex.org/W2041823554","https://openalex.org/W2093109772","https://openalex.org/W2097464745","https://openalex.org/W2101261946","https://openalex.org/W2112582577","https://openalex.org/W2115584954","https://openalex.org/W2121750345","https://openalex.org/W2123768812","https://openalex.org/W2130520294","https://openalex.org/W2136879537","https://openalex.org/W2137225583","https://openalex.org/W2139269942","https://openalex.org/W2150769028","https://openalex.org/W2166446427","https://openalex.org/W2395750323","https://openalex.org/W2396777470","https://openalex.org/W2398362606","https://openalex.org/W2406312423","https://openalex.org/W2407374891","https://openalex.org/W2534262995","https://openalex.org/W2536045881","https://openalex.org/W2652751060","https://openalex.org/W4214610555","https://openalex.org/W4230884390","https://openalex.org/W6632133026","https://openalex.org/W6712660717","https://openalex.org/W6714259624","https://openalex.org/W6739509182"],"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/W2356150353","https://openalex.org/W2354323478","https://openalex.org/W2118039276","https://openalex.org/W2078150608"],"abstract_inverted_index":{"I-vectors":[0],"are":[1,37,135],"concise":[2],"representations":[3],"of":[4,47,105],"speaker":[5,19,27,41],"characteristics.":[6],"Recent":[7],"progress":[8],"in":[9,33,70],"i-vectors":[10],"related":[11],"research":[12],"has":[13],"utilized":[14],"their":[15],"ability":[16],"to":[17,23,92],"capture":[18],"and":[20,50,82,114,128],"channel":[21],"variability":[22],"develop":[24],"efficient":[25],"automatic":[26],"verification":[28,42],"(ASV)":[29],"systems.":[30],"Inter-speaker":[31],"relationships":[32],"the":[34,71,106],"i-vector":[35,72],"space":[36],"non-linear.":[38],"Accomplishing":[39],"effective":[40],"requires":[43],"a":[44,55],"good":[45],"modeling":[46],"these":[48],"non-linearities":[49],"can":[51,64],"be":[52,65],"cast":[53],"as":[54],"machine":[56],"learning":[57],"problem.":[58],"Kernel":[59],"partial":[60],"least":[61],"squares":[62],"(KPLS)":[63],"used":[66],"for":[67],"discriminative":[68],"training":[69,79],"space.":[73],"However,":[74],"this":[75],"framework":[76],"suffers":[77],"from":[78],"data":[80,112],"imbalance":[81],"asymmetric":[83],"scoring.":[84],"We":[85],"use":[86],"\u201cone":[87],"shot":[88],"similarity":[89],"scoring\u201d":[90],"(OSS)":[91],"address":[93],"this.":[94],"The":[95],"resulting":[96],"ASV":[97],"system":[98],"(OSS-KPLS)":[99],"is":[100],"tested":[101],"across":[102],"several":[103],"conditions":[104],"NIST":[107],"SRE":[108],"2010":[109],"extended":[110],"core":[111],"set":[113],"compared":[115],"against":[116],"state-of-the-art":[117],"systems:":[118],"Joint":[119],"Factor":[120],"Analysis":[121,126],"(JFA),":[122],"Probabilistic":[123],"Linear":[124],"Discriminant":[125],"(PLDA),":[127],"Cosine":[129],"Distance":[130],"Scoring":[131],"(CDS)":[132],"classifiers.":[133],"Improvements":[134],"shown.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}