{"id":"https://openalex.org/W2164240571","doi":"https://doi.org/10.1109/asru.2011.6163922","title":"iVector-based discriminative adaptation for automatic speech recognition","display_name":"iVector-based discriminative adaptation for automatic speech recognition","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2164240571","doi":"https://doi.org/10.1109/asru.2011.6163922","mag":"2164240571"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Pavel Matejka","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008717681","display_name":"Ond\u0159ej Glembek","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Glembek","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"157"},"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":0.9987000226974487,"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":0.9976999759674072,"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":0.9152914881706238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8026416301727295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7724963426589966},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7320055365562439},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5906115770339966},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5897488594055176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5487242937088013},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5113201141357422},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43391096591949463}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9152914881706238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8026416301727295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724963426589966},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7320055365562439},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5906115770339966},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5897488594055176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5487242937088013},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5113201141357422},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43391096591949463},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2011.6163922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"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":25,"referenced_works":["https://openalex.org/W156213964","https://openalex.org/W159523117","https://openalex.org/W233468731","https://openalex.org/W1599512239","https://openalex.org/W1981706894","https://openalex.org/W2002342963","https://openalex.org/W2101261946","https://openalex.org/W2120019470","https://openalex.org/W2121546856","https://openalex.org/W2125610823","https://openalex.org/W2126033156","https://openalex.org/W2132215870","https://openalex.org/W2140251298","https://openalex.org/W2141279928","https://openalex.org/W2146635662","https://openalex.org/W2150769028","https://openalex.org/W2165125849","https://openalex.org/W2406312423","https://openalex.org/W6606552489","https://openalex.org/W6608993760","https://openalex.org/W6678800364","https://openalex.org/W6679556679","https://openalex.org/W6680699714","https://openalex.org/W6684465098","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W3148366653","https://openalex.org/W1560125148"],"abstract_inverted_index":{"We":[0,85],"presented":[1],"a":[2,37,96],"novel":[3],"technique":[4],"for":[5,46],"discriminative":[6],"feature-level":[7],"adaptation":[8,93,104],"of":[9,16,62],"automatic":[10],"speech":[11,33,75],"recognition":[12],"system.":[13],"The":[14,77],"concept":[15],"iVectors":[17,45,71],"popular":[18],"in":[19],"Speaker":[20],"Recognition":[21],"is":[22,36],"used":[23],"to":[24,65,73,88,91],"extract":[25,66],"information":[26,69],"about":[27],"speaker":[28],"or":[29],"acoustic":[30],"environment":[31],"from":[32,70],"segment.":[34],"iVector":[35],"low-dimensional":[38],"fixed-length":[39],"representing":[40],"such":[41],"information.":[42],"To":[43],"utilized":[44],"adaptation,":[47],"Region":[48],"Dependent":[49],"Linear":[50],"Transforms":[51],"(RDLT)":[52],"are":[53],"discriminatively":[54],"trained":[55],"using":[56],"MPE":[57],"criterion":[58],"on":[59,81],"large":[60],"amount":[61],"annotated":[63],"data":[64],"the":[67],"relevant":[68],"and":[72],"compensate":[74],"feature.":[76],"approach":[78],"was":[79],"tested":[80],"standard":[82,102],"CTS":[83],"data.":[84],"found":[86],"it":[87],"be":[89],"complementary":[90],"common":[92],"techniques.":[94],"On":[95],"well":[97],"tuned":[98],"RDLT":[99],"system":[100],"with":[101],"CMLLR":[103],"we":[105],"reached":[106],"0.8%":[107],"additive":[108],"absolute":[109],"WER":[110],"improvement.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}