{"id":"https://openalex.org/W2125007694","doi":"https://doi.org/10.1109/icassp.2012.6289012","title":"Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition","display_name":"Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2125007694","doi":"https://doi.org/10.1109/icassp.2012.6289012","mag":"2125007694"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of 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/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"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":["DE","GB"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","Spoken Language Systems, University of Saarland, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Spoken Language Systems, University of Saarland, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"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, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4877","last_page":"4880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9966999888420105,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9944000244140625,"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/subspace-topology","display_name":"Subspace topology","score":0.8538342714309692},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.8012433052062988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.775334358215332},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5878130197525024},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5822558403015137},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5759176015853882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.568442702293396},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5519770383834839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5479854345321655},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4916015565395355},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44376567006111145},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43102163076400757},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4191644787788391},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4011213481426239},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.37788140773773193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16185134649276733},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10812178254127502}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.8538342714309692},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.8012433052062988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775334358215332},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5878130197525024},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5822558403015137},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5759176015853882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.568442702293396},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5519770383834839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479854345321655},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4916015565395355},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44376567006111145},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43102163076400757},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4191644787788391},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4011213481426239},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.37788140773773193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16185134649276733},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10812178254127502},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2012.6289012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.250.979","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.250.979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/llu-icassp-2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.7692","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.7692","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/aghoshal/pubs/icassp12-sgmm_map_xling.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/5a89cddd-7adf-4d6e-9b9f-7843281b1440","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/maximum-a-posteriori-adaptation-of-subspace-gaussian-mixture-models-for-crosslingual-speech-recognition(5a89cddd-7adf-4d6e-9b9f-7843281b1440).html","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/5a89cddd-7adf-4d6e-9b9f-7843281b1440","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5a89cddd-7adf-4d6e-9b9f-7843281b1440","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"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":"Lu, L, Ghoshal, A & Renals, S 2012, Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition. in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on. Institute of Electrical and Electronics Engineers, pp. 4877-4880. https://doi.org/10.1109/ICASSP.2012.6289012","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W179430498","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1981706894","https://openalex.org/W1991180839","https://openalex.org/W2078537874","https://openalex.org/W2123798005","https://openalex.org/W2138534187","https://openalex.org/W2144059450","https://openalex.org/W3148198191","https://openalex.org/W3179903767","https://openalex.org/W6602682705","https://openalex.org/W6793073298"],"related_works":["https://openalex.org/W1503532423","https://openalex.org/W1967494390","https://openalex.org/W245717845","https://openalex.org/W3013496002","https://openalex.org/W2465363361","https://openalex.org/W2896820906","https://openalex.org/W2101542441","https://openalex.org/W4284711868","https://openalex.org/W2283950057","https://openalex.org/W1906819494"],"abstract_inverted_index":{"This":[0],"paper":[1],"concerns":[2],"cross-lingual":[3,48,123],"acoustic":[4],"modeling":[5],"in":[6,21,115],"the":[7,32,37,56,67,83,91,106,110,122],"case":[8],"when":[9,54],"there":[10],"are":[11,52],"limited":[12],"target":[13,33,57,70,142],"language":[14,34,143],"resources.":[15],"We":[16,72],"build":[17],"on":[18,90,105],"an":[19],"approach":[20,80,113],"which":[22,59],"a":[23,64,74,76,98],"subspace":[24,95],"Gaussian":[25,101],"mixture":[26],"model":[27],"(SGMM)":[28],"is":[29],"adapted":[30],"to":[31,63,81],"by":[35],"reusing":[36],"globally":[38],"shared":[39],"parameters":[40,51,96],"estimated":[41],"from":[42],"out-of-language":[43],"training":[44,55,133],"data.":[45,144],"In":[46,86],"current":[47],"systems,":[49],"these":[50],"fixed":[53],"system,":[58],"can":[60],"give":[61],"rise":[62],"mismatch":[65],"between":[66],"source":[68],"and":[69,126,138],"systems.":[71],"investigate":[73],"maximum":[75,130],"posteriori":[77],"(MAP)":[78],"adaptation":[79,92,112],"alleviate":[82],"potential":[84],"mismatch.":[85],"particular,":[87],"we":[88],"focus":[89],"of":[93,141],"phonetic":[94],"using":[97,109,129],"matrix":[99],"variate":[100],"prior":[102],"distribution.":[103],"Experiments":[104],"GlobalPhone":[107],"corpus":[108],"MAP":[111],"results":[114],"word":[116],"error":[117],"rate":[118],"reductions,":[119],"compared":[120],"with":[121,135],"base-line":[124],"systems":[125,127],"updated":[128],"likelihood,":[131],"for":[132],"conditions":[134],"1":[136],"hour":[137],"5":[139],"hours":[140]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}