{"id":"https://openalex.org/W2044048901","doi":"https://doi.org/10.1109/tasl.2013.2281575","title":"Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition","display_name":"Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition","publication_year":2013,"publication_date":"2013-09-16","ids":{"openalex":"https://openalex.org/W2044048901","doi":"https://doi.org/10.1109/tasl.2013.2281575","mag":"2044048901"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2281575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2281575","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":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/25144208/liang_taslp12_crosslingual.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research/School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":5.3545,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9536879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"17","last_page":"27"},"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":0.9998999834060669,"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":0.9994999766349792,"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":0.7953164577484131},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6865960359573364},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.645331621170044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6424683928489685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537994921207428},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4393453896045685},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42334115505218506},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4163597524166107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3408752679824829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953164577484131},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6865960359573364},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.645331621170044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6424683928489685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537994921207428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4393453896045685},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42334115505218506},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4163597524166107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3408752679824829},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tasl.2013.2281575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2281575","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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/47fce1ff-2ffc-486f-b19e-b8f99bc98945","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/47fce1ff-2ffc-486f-b19e-b8f99bc98945","pdf_url":"https://www.research.ed.ac.uk/files/25144208/liang_taslp12_crosslingual.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Ghoshal, A & Renals, S 2014, 'Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 22, no. 1, pp. 17-27. https://doi.org/10.1109/TASL.2013.2281575","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.8500","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.8500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2013/lu_crosslingual13.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.491.1178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.491.1178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/llu/pdf/lu_crosslingual13.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/47fce1ff-2ffc-486f-b19e-b8f99bc98945","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/47fce1ff-2ffc-486f-b19e-b8f99bc98945","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Ghoshal, A & Renals, S 2014, 'Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 22, no. 1, pp. 17-27. https://doi.org/10.1109/TASL.2013.2281575","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/47fce1ff-2ffc-486f-b19e-b8f99bc98945","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/47fce1ff-2ffc-486f-b19e-b8f99bc98945","pdf_url":"https://www.research.ed.ac.uk/files/25144208/liang_taslp12_crosslingual.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Ghoshal, A & Renals, S 2014, 'Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 22, no. 1, pp. 17-27. https://doi.org/10.1109/TASL.2013.2281575","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2044048901.pdf","grobid_xml":"https://content.openalex.org/works/W2044048901.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W66627554","https://openalex.org/W73572011","https://openalex.org/W179430498","https://openalex.org/W1524333225","https://openalex.org/W1526516369","https://openalex.org/W1554944419","https://openalex.org/W1763005514","https://openalex.org/W1846073453","https://openalex.org/W1980850109","https://openalex.org/W1981706894","https://openalex.org/W1984514442","https://openalex.org/W1991180839","https://openalex.org/W1994126409","https://openalex.org/W1995002252","https://openalex.org/W2013205774","https://openalex.org/W2033436836","https://openalex.org/W2034870236","https://openalex.org/W2047497400","https://openalex.org/W2067474491","https://openalex.org/W2078537874","https://openalex.org/W2079508481","https://openalex.org/W2096672142","https://openalex.org/W2101188291","https://openalex.org/W2108586753","https://openalex.org/W2109449402","https://openalex.org/W2111306781","https://openalex.org/W2120209245","https://openalex.org/W2123798005","https://openalex.org/W2125007694","https://openalex.org/W2131042651","https://openalex.org/W2132534451","https://openalex.org/W2138534187","https://openalex.org/W2144059450","https://openalex.org/W2147276082","https://openalex.org/W2147768505","https://openalex.org/W2165355580","https://openalex.org/W2165712214","https://openalex.org/W2296616510","https://openalex.org/W2407897255","https://openalex.org/W3148198191","https://openalex.org/W3179903767","https://openalex.org/W4250955649","https://openalex.org/W6601939441","https://openalex.org/W6602682705","https://openalex.org/W6602987424","https://openalex.org/W6631362777","https://openalex.org/W6638728282","https://openalex.org/W6674389704","https://openalex.org/W6684184871"],"related_works":["https://openalex.org/W2151402979","https://openalex.org/W2155089829","https://openalex.org/W2152494161","https://openalex.org/W1981706894","https://openalex.org/W1541505381","https://openalex.org/W2147207799","https://openalex.org/W2041903645","https://openalex.org/W2042327336","https://openalex.org/W182076448","https://openalex.org/W2099826692"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"cross-lingual":[3,158],"acoustic":[4,18,68],"modeling":[5],"in":[6,137],"the":[7,17,30,44,50,60,81,94,98,141,144,149,166,181],"context":[8],"of":[9,32,76,134,148],"subspace":[10,135],"Gaussian":[11],"mixture":[12],"models":[13,69],"(SGMMs).":[14],"SGMMs":[15],"factorize":[16],"model":[19,36,167],"parameters":[20,53,61,84,96,136,147],"into":[21],"a":[22,33,66,130],"set":[23],"that":[24,40,49],"is":[25,41,111,162],"globally":[26],"shared":[27],"between":[28,56,143],"all":[29],"states":[31],"hidden":[34],"Markov":[35],"(HMM)":[37],"and":[38,91,120,151,157],"another":[39],"specific":[42],"to":[43,113,122,139,164],"HMM":[45],"states.":[46],"We":[47,127,172],"demonstrate":[48],"SGMM":[51,82,145],"global":[52,83,146],"are":[54,62],"transferable":[55],"languages,":[57,90],"particularly":[58,115],"when":[59],"trained":[63,72],"multilingually.":[64],"As":[65],"result,":[67],"may":[70],"be":[71,114],"using":[73,104],"limited":[74],"amounts":[75],"transcribed":[77],"audio":[78],"by":[79,170,178],"borrowing":[80],"from":[85],"one":[86],"or":[87],"more":[88],"source":[89,150],"only":[92],"training":[93,161],"state-specific":[95],"on":[97,180],"target":[99,152],"language":[100],"audio.":[101],"Model":[102],"regularization":[103],"\u2113":[105],"<sub":[106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[108],"-norm":[109],"penalty":[110],"shown":[112],"effective":[116],"at":[117],"avoiding":[118],"overtraining":[119],"leading":[121],"lower":[123],"word":[124],"error":[125],"rates.":[126],"investigate":[128],"maximum":[129],"posteriori":[131],"(MAP)":[132],"adaptation":[133],"order":[138],"reduce":[140,165],"mismatch":[142],"languages.":[153],"In":[154],"addition,":[155],"monolingual":[156],"speaker":[159],"adaptive":[160],"used":[163],"variance":[168],"introduced":[169],"speakers.":[171],"have":[173],"systematically":[174],"evaluated":[175],"these":[176],"techniques":[177],"experiments":[179],"GlobalPhone":[182],"corpus.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}