{"id":"https://openalex.org/W1989549063","doi":"https://doi.org/10.1109/icassp.2013.6639201","title":"KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition","display_name":"KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1989549063","doi":"https://doi.org/10.1109/icassp.2013.6639201","mag":"1989549063"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":true,"raw_author_name":"Dong Yu","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/A5103119755","display_name":"Kaisheng Yao","orcid":"https://orcid.org/0000-0002-8949-9367"},"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":"Kaisheng Yao","raw_affiliation_strings":["Online Services Division, Microsoft Corporation, Redmond, WA, USA","Online Services Div., Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Online Services Division, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Online Services Div., Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341891","display_name":"Hang Su","orcid":"https://orcid.org/0000-0002-6877-6783"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["Microsoft Research Asia, Beijing, Beijing, CN","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438769","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-1583-641X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":74.224,"has_fulltext":false,"cited_by_count":416,"citation_normalized_percentile":{"value":0.99933295,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7893","last_page":"7897"},"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":0.9984999895095825,"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":0.998199999332428,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7999880909919739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7202227711677551},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520097255706787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5744530558586121},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5365337133407593},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5254665613174438},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5182899832725525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5114971399307251},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5094223618507385},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.48205170035362244},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.41916167736053467},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4159563183784485},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.41470810770988464}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7999880909919739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202227711677551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520097255706787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5744530558586121},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5365337133407593},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5254665613174438},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5182899832725525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114971399307251},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5094223618507385},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.48205170035362244},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.41916167736053467},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4159563183784485},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.41470810770988464},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W185613617","https://openalex.org/W217970951","https://openalex.org/W1513862252","https://openalex.org/W1537275613","https://openalex.org/W1722135069","https://openalex.org/W1891007208","https://openalex.org/W1987238397","https://openalex.org/W1993882792","https://openalex.org/W2038550700","https://openalex.org/W2062164080","https://openalex.org/W2076794394","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2095168618","https://openalex.org/W2096170322","https://openalex.org/W2117824967","https://openalex.org/W2130037349","https://openalex.org/W2131241448","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2157711090","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2162042984","https://openalex.org/W2169434751","https://openalex.org/W2173880944","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2399979637","https://openalex.org/W2403195671","https://openalex.org/W2941108253","https://openalex.org/W2950182411","https://openalex.org/W4230820110","https://openalex.org/W6607553906","https://openalex.org/W6660213180","https://openalex.org/W6684010798","https://openalex.org/W6685119187"],"related_works":["https://openalex.org/W2353325398","https://openalex.org/W2558599680","https://openalex.org/W2367608902","https://openalex.org/W2359823483","https://openalex.org/W2392667367","https://openalex.org/W2381559703","https://openalex.org/W2353027778","https://openalex.org/W2381835873","https://openalex.org/W2938137567","https://openalex.org/W4386939572"],"abstract_inverted_index":{"We":[0,97],"propose":[1],"a":[2,20,44],"novel":[3],"regularized":[4],"adaptation":[5,43,50,95,134,153,160],"technique":[6,55,135],"for":[7],"context":[8],"dependent":[9],"deep":[10],"neural":[11],"network":[12],"hidden":[13,27],"Markov":[14],"models":[15],"(CD-DNN-HMMs).":[16],"The":[17,34,54],"CD-DNN-HMM":[18,41,149],"has":[19],"large":[21,26],"output":[22],"layer":[23],"and":[24,123,125,158],"many":[25],"layers,":[28],"each":[29],"with":[30],"thousands":[31],"of":[32,37],"neurons.":[33],"huge":[35],"number":[36],"parameters":[38],"in":[39,57,110],"the":[40,49,61,66,71,80,94,107,111,132,143],"makes":[42],"challenging":[45],"task,":[46],"esp.":[47],"when":[48],"set":[51],"is":[52,85,103],"small.":[53],"developed":[56],"this":[58,101],"paper":[59],"adapts":[60],"model":[62,73],"conservatively":[63],"by":[64,87],"forcing":[65],"senone":[67],"distribution":[68,109],"estimated":[69],"from":[70,79],"adapted":[72],"to":[74,77,93,105],"be":[75],"close":[76],"that":[78,99,131],"unadapted":[81],"model.":[82],"This":[83],"constraint":[84],"realized":[86],"adding":[88],"Kullback-Leibler":[89],"divergence":[90],"(KLD)":[91],"regularization":[92,102],"criterion.":[96],"show":[98],"applying":[100],"equivalent":[104],"changing":[106],"target":[108],"conventional":[112],"backpropagation":[113],"algorithm.":[114],"Experiments":[115],"on":[116],"Xbox":[117],"voice":[118],"search,":[119],"short":[120],"message":[121],"dictation,":[122],"Switchboard":[124],"lecture":[126],"speech":[127],"transcription":[128],"tasks":[129],"demonstrate":[130],"proposed":[133],"can":[136],"provide":[137],"2%-30%":[138],"relative":[139],"error":[140],"reduction":[141],"against":[142],"already":[144],"very":[145],"strong":[146],"speaker":[147],"independent":[148],"systems":[150],"using":[151],"different":[152],"sets":[154],"under":[155],"both":[156],"supervised":[157],"unsupervised":[159],"setups.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":43},{"year":2018,"cited_by_count":45},{"year":2017,"cited_by_count":53},{"year":2016,"cited_by_count":69},{"year":2015,"cited_by_count":47},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}