{"id":"https://openalex.org/W2123798005","doi":"https://doi.org/10.1109/icassp.2010.5495646","title":"Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models","display_name":"Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2123798005","doi":"https://doi.org/10.1109/icassp.2010.5495646","mag":"2123798005"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/203450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/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":true,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660964","display_name":"Petr Schwarz","orcid":"https://orcid.org/0000-0002-2281-9637"},"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":"Petr Schwarz","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050672063","display_name":"Mohit Agarwal","orcid":"https://orcid.org/0000-0001-5340-1359"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohit Agarwal","raw_affiliation_strings":["IIIT Allahabad, India","IIIT Allahabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT Allahabad, India","institution_ids":["https://openalex.org/I26072440"]},{"raw_affiliation_string":"IIIT Allahabad, India#TAB#","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002721994","display_name":"Pinar Akyazi","orcid":null},"institutions":[{"id":"https://openalex.org/I204585392","display_name":"Usak University","ror":"https://ror.org/05es91y67","country_code":"TR","type":"education","lineage":["https://openalex.org/I204585392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Pinar Akyazi","raw_affiliation_strings":["Bo\u02c7azi\u00e7i University, Turkey","Bo\u00bfazi\u00e7i University, Turkey"],"affiliations":[{"raw_affiliation_string":"Bo\u02c7azi\u00e7i University, Turkey","institution_ids":["https://openalex.org/I204585392"]},{"raw_affiliation_string":"Bo\u00bfazi\u00e7i University, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104312750","display_name":"Kai Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Feng","raw_affiliation_strings":["HKUST, Hong Kong, Hong Kong, China","[HKUST, Hong Kong, China]"],"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]},{"raw_affiliation_string":"[HKUST, Hong Kong, China]","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Saarland University, Germany","Saarland Univ., Germany"],"affiliations":[{"raw_affiliation_string":"Saarland University, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland Univ., Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"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":["Brno University of Technology, Czech Republic","Brno University of Technology,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048489894","display_name":"Nagendra Kumar Goel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagendra Goel","raw_affiliation_strings":["Virginia, USA"],"affiliations":[{"raw_affiliation_string":"Virginia, USA","institution_ids":[]}]},{"author_position":"middle","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":["Brno University of Technology, Czech Republic","Brno University of Technology,Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","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":"Ariya Rastrow","raw_affiliation_strings":["Johns Hopkins University, MD, USA","[Johns Hopkins University, MD, USA]"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard C. Rose","raw_affiliation_strings":["McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"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":"Samuel Thomas","raw_affiliation_strings":["Johns Hopkins University, MD, USA","[Johns Hopkins University, MD, USA]"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":7,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5042273299"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":25.6501,"has_fulltext":false,"cited_by_count":159,"citation_normalized_percentile":{"value":0.99619779,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9980999827384949,"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":0.9972000122070312,"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/subspace-topology","display_name":"Subspace topology","score":0.9031230211257935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7464948296546936},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7029645442962646},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6743562817573547},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.637956440448761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5812259912490845},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5667485594749451},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5046931505203247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48798173666000366},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.478387713432312},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4320669174194336},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42936161160469055},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35186612606048584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3424791991710663},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2621443271636963},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0739496648311615}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.9031230211257935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464948296546936},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7029645442962646},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6743562817573547},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.637956440448761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5812259912490845},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5667485594749451},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5046931505203247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48798173666000366},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.478387713432312},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4320669174194336},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42936161160469055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35186612606048584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3424791991710663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2621443271636963},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0739496648311615},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:203450","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:203450","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W179430498","https://openalex.org/W1526995323","https://openalex.org/W2047497400","https://openalex.org/W2090861223","https://openalex.org/W2130086010","https://openalex.org/W2130414229","https://openalex.org/W2134260474","https://openalex.org/W2151402979","https://openalex.org/W2166637769","https://openalex.org/W2407897255","https://openalex.org/W2729906263","https://openalex.org/W6631419337","https://openalex.org/W6679469920","https://openalex.org/W6680151373","https://openalex.org/W6714284179","https://openalex.org/W6890491316"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2151402979","https://openalex.org/W2160650576","https://openalex.org/W2126322296","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2955724459","https://openalex.org/W2163537793","https://openalex.org/W2037769829"],"abstract_inverted_index":{"Although":[0],"research":[1],"has":[2,11,27,63],"previously":[3],"been":[4,12,28],"done":[5],"on":[6,44],"multilingual":[7,49],"speech":[8,50],"recognition,":[9,51],"it":[10],"found":[13],"to":[14,18,29,48,67,97],"be":[15,114],"very":[16,128],"difficult":[17],"improve":[19],"over":[20],"separately":[21],"trained":[22],"systems.":[23],"The":[24,107],"usual":[25],"approach":[26,47],"use":[30,76],"some":[31],"kind":[32],"of":[33,102,131],"\u201cuniversal":[34],"phone":[35,55],"set\u201d":[36],"that":[37,70,109],"covers":[38],"multiple":[39],"languages.":[40,74,117],"We":[41,75,118],"report":[42],"experiments":[43],"a":[45,77,80,93,100],"different":[46],"in":[52,99],"which":[53],"the":[54,61,103],"sets":[56],"are":[57,71,88],"entirely":[58],"distinct":[59],"but":[60],"model":[62,78],"parameters":[64,108],"not":[65],"tied":[66],"specific":[68],"states":[69],"shared":[72,115],"across":[73,116],"called":[79],"\u201cSubspace":[81],"Gaussian":[82,89],"Mixture":[83,90],"Model\u201d":[84],"where":[85],"states'":[86],"distributions":[87],"Models":[91],"with":[92,123,127],"common":[94],"structure,":[95],"constrained":[96],"lie":[98],"subspace":[101,112],"total":[104],"parameter":[105],"space.":[106],"define":[110],"this":[111,124],"can":[113],"obtain":[119],"substantial":[120],"WER":[121],"improvements":[122],"approach,":[125],"especially":[126],"small":[129],"amounts":[130],"in-language":[132],"training":[133],"data.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":29},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
