{"id":"https://openalex.org/W2397529076","doi":"https://doi.org/10.21437/interspeech.2013-263","title":"Noise adaptive training for subspace Gaussian mixture models","display_name":"Noise adaptive training for subspace Gaussian mixture models","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2397529076","doi":"https://doi.org/10.21437/interspeech.2013-263","mag":"2397529076"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-263","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/7e2c4482-d486-4cd7-b171-4da575691899","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, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University 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, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University 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, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University 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":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.7616915702819824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314130067825317},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6195047497749329},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6103516221046448},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5644234418869019},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5312488079071045},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5136803984642029},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4802439510822296},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46380212903022766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4206579327583313},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38031068444252014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34960126876831055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33294975757598877},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08424842357635498},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06767874956130981}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7616915702819824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314130067825317},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6195047497749329},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6103516221046448},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5644234418869019},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5312488079071045},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5136803984642029},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4802439510822296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46380212903022766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4206579327583313},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38031068444252014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34960126876831055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33294975757598877},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08424842357635498},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06767874956130981},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2013-263","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7e2c4482-d486-4cd7-b171-4da575691899","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2013/i13_3492.html","pdf_url":"http://hdl.handle.net/20.500.11820/7e2c4482-d486-4cd7-b171-4da575691899","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":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.9449","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9449","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/lu2013noise.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/7e2c4482-d486-4cd7-b171-4da575691899","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2013/i13_3492.html","pdf_url":"http://hdl.handle.net/20.500.11820/7e2c4482-d486-4cd7-b171-4da575691899","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":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","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/W2397529076.pdf","grobid_xml":"https://content.openalex.org/works/W2397529076.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W161419836","https://openalex.org/W346349565","https://openalex.org/W1573570773","https://openalex.org/W1599512239","https://openalex.org/W1981706894","https://openalex.org/W1989389005","https://openalex.org/W1991180839","https://openalex.org/W2003486321","https://openalex.org/W2024490156","https://openalex.org/W2063291689","https://openalex.org/W2067117291","https://openalex.org/W2106714211","https://openalex.org/W2111093880","https://openalex.org/W2115281877","https://openalex.org/W2118497033","https://openalex.org/W2123798005","https://openalex.org/W2123840324","https://openalex.org/W2126597753","https://openalex.org/W2136545411","https://openalex.org/W2146423524","https://openalex.org/W2155445312","https://openalex.org/W2163648514","https://openalex.org/W2404126548","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2151402979","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4401571093","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Noise":[0],"adaptive":[1,80,125,129],"training":[2,15],"(NAT)":[3],"is":[4,83],"an":[5,92],"effective":[6],"approach":[7],"to":[8,53,91,98,122],"normalise":[9],"the":[10,14,20,60,64,68,73,100,107,112],"environmental":[11],"distortions":[12],"in":[13],"data.":[16],"This":[17],"paper":[18],"investigates":[19],"model-based":[21],"NAT":[22,110],"scheme":[23],"using":[24],"joint":[25,133],"uncertainty":[26,134],"decoding":[27],"(JUD)":[28],"for":[29],"subspace":[30,136],"Gaussian":[31,46,56,137],"mixture":[32,138],"models":[33,139],"(SGMMs).":[34],"A":[35],"typical":[36],"SGMM":[37,101],"acoustic":[38,102],"model":[39,103],"has":[40],"much":[41],"larger":[42],"number":[43],"of":[44],"surface":[45],"components,":[47],"which":[48,89],"makes":[49],"it":[50],"computationally":[51],"infeasible":[52],"compensate":[54],"each":[55],"explicitly.":[57],"JUD":[58,82],"tackles":[59],"problem":[61],"by":[62],"sharing":[63],"compensation":[65],"parameters":[66],"among":[67],"Gaussians":[69],"and":[70,75,116],"hence":[71],"reduces":[72],"computational":[74],"memory":[76],"demands.":[77],"For":[78],"noise":[79,131],"training,":[81,130],"reformulated":[84],"into":[85],"a":[86],"generative":[87],"model,":[88],"leads":[90],"efficient":[93],"expectation-maximisation":[94],"(EM)":[95],"based":[96],"algorithm":[97],"update":[99],"parameters.":[104],"We":[105],"evaluated":[106],"SGMMs":[108],"with":[109],"on":[111],"Aurora":[113],"4":[114],"database,":[115],"obtained":[117],"higher":[118],"recognition":[119],"accuracy":[120],"compared":[121],"systems":[123],"without":[124],"training.":[126],"Index":[127],"Terms:":[128],"robustness,":[132],"decoding,":[135]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}