{"id":"https://openalex.org/W2115584954","doi":"https://doi.org/10.1109/icassp.2011.5947548","title":"A partial least squares framework for speaker recognition","display_name":"A partial least squares framework for speaker recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2115584954","doi":"https://doi.org/10.1109/icassp.2011.5947548","mag":"2115584954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]},{"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":true,"raw_author_name":"Balaji Vasan Srinivasan","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"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"]},{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry N. Zotkin","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"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/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]},{"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":"Ramani Duraiswami","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, Department of Computer Science & UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059650977"],"corresponding_institution_ids":["https://openalex.org/I2802964274","https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":3.0817,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92137931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2004","issue":null,"first_page":"5276","last_page":"5279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9922000169754028,"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"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7819774150848389},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7740102410316467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.672002375125885},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6649426221847534},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6632826924324036},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6343575119972229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5872761607170105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5549274682998657},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5288912653923035},{"id":"https://openalex.org/keywords/partial-least-squares-regression","display_name":"Partial least squares regression","score":0.520216166973114},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.508897066116333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031663775444031},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44635024666786194},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4281967580318451},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24035105109214783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19736811518669128}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7819774150848389},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7740102410316467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672002375125885},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6649426221847534},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6632826924324036},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6343575119972229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5872761607170105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5549274682998657},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5288912653923035},{"id":"https://openalex.org/C22354355","wikidata":"https://www.wikidata.org/wiki/Q422009","display_name":"Partial least squares regression","level":2,"score":0.520216166973114},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.508897066116333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031663775444031},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44635024666786194},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4281967580318451},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24035105109214783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19736811518669128},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.204.6425","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.204.6425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/%7Eramani/pubs/PLS_ICASSP2011_2969.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W609024325","https://openalex.org/W2041823554","https://openalex.org/W2097464745","https://openalex.org/W2111206974","https://openalex.org/W2121750345","https://openalex.org/W2136879537","https://openalex.org/W2137225583","https://openalex.org/W2144760012","https://openalex.org/W2154278880","https://openalex.org/W2398362606","https://openalex.org/W2534262995","https://openalex.org/W6618784633","https://openalex.org/W6676602738","https://openalex.org/W6712660717"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2181956362","https://openalex.org/W2136153680","https://openalex.org/W2972577568","https://openalex.org/W2148323604"],"abstract_inverted_index":{"Modern":[0],"approaches":[1,38],"to":[2,39,98,102,105,111],"speaker":[3,113],"recognition":[4],"(verification)":[5],"operate":[6],"in":[7],"a":[8,20,27,35,52,67,112],"space":[9],"of":[10,15,19,37,118],"\"supervectors\"":[11],"created":[12],"via":[13],"concatenation":[14],"the":[16,56,74,108],"mean":[17],"vectors":[18],"Gaussian":[21],"mixture":[22],"model":[23,30,40],"(GMM)":[24],"adapted":[25],"from":[26],"universal":[28],"background":[29],"(UBM).":[31],"In":[32],"this":[33],"space,":[34],"number":[36],"inter-class":[41],"separability":[42],"and":[43,90,101],"nuisance":[44],"attribute":[45],"variability":[46,57],"have":[47],"been":[48],"proposed.":[49],"We":[50],"develop":[51],"method":[53,82,95],"for":[54,78],"modeling":[55,70],"associated":[58],"with":[59],"each":[60,79],"class":[61],"(speaker)":[62],"by":[63],"using":[64],"partial-least-squares":[65],"-":[66],"latent":[68],"variable":[69],"technique,":[71],"which":[72],"isolates":[73],"most":[75],"informative":[76],"subspace":[77,109],"speaker.":[80],"The":[81,94],"is":[83,96],"tested":[84],"on":[85,114],"NIST":[86],"SRE":[87],"2008":[88],"data":[89,116],"provides":[91],"promising":[92],"results.":[93],"shown":[97],"be":[99,103],"noise-robust":[100],"able":[104],"efficiently":[106],"learn":[107],"corresponding":[110],"training":[115],"consisting":[117],"multiple":[119],"utterances.":[120]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}