{"id":"https://openalex.org/W2095168618","doi":"https://doi.org/10.1109/tasl.2012.2227738","title":"The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition","display_name":"The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition","publication_year":2012,"publication_date":"2012-11-14","ids":{"openalex":"https://openalex.org/W2095168618","doi":"https://doi.org/10.1109/tasl.2012.2227738","mag":"2095168618"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2227738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2227738","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"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":"Li Deng","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":"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":3,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":8.1922,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.98780488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"21","issue":"2","first_page":"388","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.991599977016449,"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":0.7273120880126953},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.674475908279419},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6547815799713135},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6366134881973267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.626785397529602},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5841690301895142},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5498438477516174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5459592938423157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5238195061683655},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.5073005557060242},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4681684672832489},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4618069529533386},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4588187336921692},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4573078453540802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4464494585990906},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4322876036167145},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18038985133171082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1502431035041809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273120880126953},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.674475908279419},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6547815799713135},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6366134881973267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.626785397529602},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5841690301895142},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5498438477516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5459592938423157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5238195061683655},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.5073005557060242},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4681684672832489},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4618069529533386},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4588187336921692},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4573078453540802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4464494585990906},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4322876036167145},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18038985133171082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1502431035041809},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2012.2227738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2227738","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.337.9580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.337.9580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.2980","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/177443/DTNN-TASLP2012-Proof.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320332953","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W5939791","https://openalex.org/W185613617","https://openalex.org/W196214544","https://openalex.org/W217970951","https://openalex.org/W1977908343","https://openalex.org/W1983334819","https://openalex.org/W1993882792","https://openalex.org/W2024165284","https://openalex.org/W2076794394","https://openalex.org/W2096635587","https://openalex.org/W2100495367","https://openalex.org/W2112796928","https://openalex.org/W2112984492","https://openalex.org/W2135217348","https://openalex.org/W2141778357","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2161000554","https://openalex.org/W2169189000","https://openalex.org/W2169434751","https://openalex.org/W2394932179","https://openalex.org/W2465562739","https://openalex.org/W6600239486","https://openalex.org/W6607553906","https://openalex.org/W6607974698","https://openalex.org/W6608710415","https://openalex.org/W6679935232","https://openalex.org/W6681419218","https://openalex.org/W6683775911","https://openalex.org/W6711962127","https://openalex.org/W6803034309"],"related_works":["https://openalex.org/W2896134808","https://openalex.org/W3172436493","https://openalex.org/W4287164812","https://openalex.org/W2957492749","https://openalex.org/W1887135636","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W3213150849","https://openalex.org/W4285605394","https://openalex.org/W2025894073"],"abstract_inverted_index":{"The":[0,41],"recently":[1],"proposed":[2],"context-dependent":[3],"deep":[4,36,92],"neural":[5,38],"network":[6,39],"hidden":[7],"Markov":[8],"models":[9],"(CD-DNN-HMMs)":[10],"have":[11],"been":[12],"proved":[13],"highly":[14],"promising":[15],"for":[16],"large":[17],"vocabulary":[18],"speech":[19],"recognition.":[20],"In":[21,94],"this":[22,127],"paper,":[23],"we":[24,33,96,129],"develop":[25],"a":[26,56,72,120,132],"more":[27,51,163],"advanced":[28],"type":[29],"of":[30,52,149,159],"DNN,":[31],"which":[32,61,76],"call":[34],"the":[35,44,87,91,102,106,112,124,135,145,175],"tensor":[37,73,103],"(DTNN).":[40],"DTNN":[42,133],"extends":[43],"conventional":[45,107],"DNN":[46,136],"by":[47],"replacing":[48],"one":[49],"or":[50],"its":[53],"layers":[54,104,109,140],"with":[55,81,138,179],"double-projection":[57],"(DP)":[58],"layer,":[59,74],"in":[60,75,90,119],"each":[62,82],"input":[63],"vector":[64],"is":[65],"projected":[66],"into":[67],"two":[68,77],"nonlinear":[69],"subspaces,":[70],"and":[71,84,117,181,190],"subspace":[78],"projections":[79],"interact":[80],"other":[83],"jointly":[85],"predict":[86],"next":[88],"layer":[89],"architecture.":[93],"addition,":[95],"describe":[97],"an":[98],"approach":[99],"to":[100,105,123],"map":[101],"sigmoid":[108],"so":[110,141],"that":[111,142,171],"former":[113],"can":[114,130,151,161,173],"be":[115,152,162],"treated":[116],"trained":[118],"similar":[121],"way":[122],"latter.":[125],"With":[126],"mapping":[128],"consider":[131],"as":[134],"augmented":[137],"DP":[139],"not":[143],"only":[144],"BP":[146],"learning":[147],"algorithm":[148],"DTNNs":[150,160,172],"cleanly":[153],"derived":[154],"but":[155],"also":[156],"new":[157],"types":[158],"easily":[164],"developed.":[165],"Evaluation":[166],"on":[167],"Switchboard":[168],"tasks":[169],"indicates":[170],"outperform":[174],"already":[176],"high-performing":[177],"DNNs":[178],"4-5%":[180],"3%":[182],"relative":[183],"word":[184],"error":[185],"reduction,":[186],"respectively,":[187],"using":[188],"30-hr":[189],"309-hr":[191],"training":[192],"sets.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}