{"id":"https://openalex.org/W2136545411","doi":"https://doi.org/10.21437/interspeech.2012-109","title":"Noise compensation for subspace Gaussian mixture models","display_name":"Noise compensation for subspace Gaussian mixture models","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2136545411","doi":"https://doi.org/10.21437/interspeech.2012-109","mag":"2136545411"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-109","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058000820","display_name":"K. K. Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. K. Chin","raw_affiliation_strings":["Toshiba (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"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, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"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":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"306","last_page":"309"},"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":0.9994000196456909,"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":0.9965000152587891,"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/mixture-model","display_name":"Mixture model","score":0.8735523223876953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6331019401550293},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6286124587059021},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6111673712730408},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5350070595741272},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.530063807964325},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5098177790641785},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5017080307006836},{"id":"https://openalex.org/keywords/additive-white-gaussian-noise","display_name":"Additive white Gaussian noise","score":0.4820026457309723},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4751581847667694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4510088860988617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4005693793296814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3546364903450012},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.244573175907135},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07148557901382446},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05965742468833923}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8735523223876953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6331019401550293},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6286124587059021},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6111673712730408},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5350070595741272},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.530063807964325},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5098177790641785},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5017080307006836},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.4820026457309723},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4751581847667694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4510088860988617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4005693793296814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3546364903450012},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.244573175907135},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07148557901382446},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05965742468833923},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2012-109","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","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:CiteSeerX.psu:10.1.1.248.4735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.248.4735","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-is2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.8493","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.8493","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/lu-is12-sgmm_jud.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","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, Chin, K K, Ghoshal, A & Renals, S 2012, Noise Compensation for Subspace Gaussian Mixture Models. in INTERSPEECH 2012 13th Annual Conference of the International Speech Communication Association. pp. 306-309. < http://www.isca-speech.org/archive/interspeech_2012/i12_0306.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/6dda3f4e-f520-4444-93bd-cb1bce8bd90b","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":""},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136545411.pdf","grobid_xml":"https://content.openalex.org/works/W2136545411.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W75761934","https://openalex.org/W105750483","https://openalex.org/W186298718","https://openalex.org/W1502469360","https://openalex.org/W1561429093","https://openalex.org/W1573570773","https://openalex.org/W1976587308","https://openalex.org/W1981706894","https://openalex.org/W2010023285","https://openalex.org/W2035328943","https://openalex.org/W2063291689","https://openalex.org/W2106714211","https://openalex.org/W2111093880","https://openalex.org/W2111539083","https://openalex.org/W2113911479","https://openalex.org/W2115281877","https://openalex.org/W2126597753","https://openalex.org/W2147143213","https://openalex.org/W2152718950","https://openalex.org/W2155445312","https://openalex.org/W2159956931","https://openalex.org/W2280467666"],"related_works":["https://openalex.org/W2151402979","https://openalex.org/W1911817635","https://openalex.org/W2074565401","https://openalex.org/W2810224748","https://openalex.org/W2353656796","https://openalex.org/W2011915004","https://openalex.org/W1607924090","https://openalex.org/W1967187784","https://openalex.org/W2242778450","https://openalex.org/W2380803194"],"abstract_inverted_index":{"Joint":[0],"uncertainty":[1],"decoding":[2],"(JUD)":[3],"is":[4,46,110],"an":[5],"effective":[6],"model-based":[7],"noise":[8,84,122],"compensation":[9,85],"technique":[10,97],"for":[11,51],"conventional":[12,52,114],"Gaussian":[13,29,75],"mix-ture":[14],"model":[15,31,45],"(GMM)":[16],"based":[17,33],"speech":[18],"recognition":[19],"systems.":[20,92],"In":[21],"this":[22],"paper,":[23],"we":[24],"apply":[25],"JUD":[26,121],"to":[27,90],"subspace":[28],"mixture":[30],"(SGMM)":[32],"acoustic":[34,44],"models.":[35],"The":[36],"total":[37],"number":[38,79],"of":[39,58,80],"Gaus-sians":[40],"in":[41],"the":[42,56,74,95,99,104],"SGMM":[43,91],"usually":[47],"much":[48],"larger":[49],"than":[50,113],"GMMs,":[53],"which":[54,60],"limits":[55],"application":[57],"approaches":[59],"explicitly":[61],"compensate":[62],"each":[63],"Gaussian,":[64],"such":[65],"as":[66],"vector":[67],"Taylor":[68],"series":[69],"(VTS).":[70],"However,":[71],"by":[72],"clustering":[73],"components":[76],"into":[77],"a":[78],"regression":[81],"classes,":[82],"JUD-based":[83],"can":[86],"be":[87],"successfully":[88],"applied":[89],"We":[93],"evaluate":[94],"JUD/SGMM":[96],"us-ing":[98],"Aurora":[100],"4":[101],"corpus,":[102],"and":[103],"experimental":[105],"results":[106],"indicated":[107],"that":[108],"it":[109],"more":[111],"accurate":[112],"GMM-based":[115],"systems":[116],"using":[117],"either":[118],"VTS":[119],"or":[120],"compensation.":[123],"1.":[124]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"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"}