{"id":"https://openalex.org/W1993882792","doi":"https://doi.org/10.1109/tasl.2011.2109382","title":"Acoustic Modeling Using Deep Belief Networks","display_name":"Acoustic Modeling Using Deep Belief Networks","publication_year":2011,"publication_date":"2011-01-31","ids":{"openalex":"https://openalex.org/W1993882792","doi":"https://doi.org/10.1109/tasl.2011.2109382","mag":"1993882792"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2109382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2109382","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/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":["University of Toronto, Toronto, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047062711","display_name":"George E. Dahl","orcid":"https://orcid.org/0000-0002-0083-844X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George E. Dahl","raw_affiliation_strings":["University of Toronto, Toronto, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey Hinton","raw_affiliation_strings":["University of Toronto, Toronto, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":155.727,"has_fulltext":false,"cited_by_count":1746,"citation_normalized_percentile":{"value":0.99990358,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"20","issue":"1","first_page":"14","last_page":"22"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9991999864578247,"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/timit","display_name":"TIMIT","score":0.8583399653434753},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8543685674667358},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8468328714370728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414878010749817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6702182292938232},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6616368293762207},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.6333584189414978},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6243409514427185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5359426736831665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5179087519645691},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5075284242630005},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4915352761745453},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.478089302778244},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4739537239074707},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4648987352848053},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4419749975204468},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.37023985385894775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3646315336227417},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.323351114988327}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8583399653434753},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8543685674667358},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8468328714370728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414878010749817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6702182292938232},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6616368293762207},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.6333584189414978},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6243409514427185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5359426736831665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5179087519645691},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5075284242630005},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4915352761745453},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.478089302778244},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4739537239074707},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4648987352848053},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4419749975204468},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37023985385894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646315336227417},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.323351114988327},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2011.2109382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2109382","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:10.1.1.338.2670","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.338.2670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W66838807","https://openalex.org/W73112891","https://openalex.org/W99063960","https://openalex.org/W137106866","https://openalex.org/W155708904","https://openalex.org/W190289757","https://openalex.org/W811578723","https://openalex.org/W1538748823","https://openalex.org/W1553004968","https://openalex.org/W1562289873","https://openalex.org/W1647054946","https://openalex.org/W1993845689","https://openalex.org/W1994197834","https://openalex.org/W2014641584","https://openalex.org/W2027915610","https://openalex.org/W2071489795","https://openalex.org/W2077804127","https://openalex.org/W2083380015","https://openalex.org/W2100495367","https://openalex.org/W2102512139","https://openalex.org/W2103359087","https://openalex.org/W2104997912","https://openalex.org/W2110798204","https://openalex.org/W2110871230","https://openalex.org/W2116064496","https://openalex.org/W2117366282","https://openalex.org/W2125534887","https://openalex.org/W2131700150","https://openalex.org/W2131854866","https://openalex.org/W2136922672","https://openalex.org/W2139671364","https://openalex.org/W2141778357","https://openalex.org/W2142773971","https://openalex.org/W2147768505","https://openalex.org/W2150529939","https://openalex.org/W2155342818","https://openalex.org/W2159080219","https://openalex.org/W2161893161","https://openalex.org/W2165119652","https://openalex.org/W2766545043","https://openalex.org/W2913932916","https://openalex.org/W3118608800","https://openalex.org/W6601785968","https://openalex.org/W6605498254","https://openalex.org/W6675321185","https://openalex.org/W6681101923","https://openalex.org/W6683819664"],"related_works":["https://openalex.org/W2113823560","https://openalex.org/W2052112670","https://openalex.org/W2172097686","https://openalex.org/W2002052740","https://openalex.org/W2474633151","https://openalex.org/W2105153012","https://openalex.org/W2887732792","https://openalex.org/W2048014685","https://openalex.org/W3160080723","https://openalex.org/W643545633"],"abstract_inverted_index":{"Gaussian":[0,35],"mixture":[1,36],"models":[2,16,37],"are":[3,57],"currently":[4],"the":[5,10,27,80,85,95,108],"dominant":[6],"technique":[7],"for":[8,17],"modeling":[9],"emission":[11],"distribution":[12,106],"of":[13,46,53,65,68,75,110],"hidden":[14,112],"Markov":[15,113],"speech":[18],"recognition.":[19],"We":[20],"show":[21],"that":[22,42],"better":[23,101],"phone":[24],"recognition":[25],"on":[26],"TIMIT":[28],"dataset":[29],"can":[30],"be":[31],"achieved":[32],"by":[33,38],"replacing":[34],"deep":[39],"neural":[40],"networks":[41,56],"contain":[43],"many":[44],"layers":[45],"features":[47,96],"and":[48],"a":[49,61,66,104],"very":[50],"large":[51],"number":[52],"parameters.":[54],"These":[55],"first":[58],"pre-trained":[59],"as":[60],"multi-layer":[62],"generative":[63,81],"model":[64],"window":[67],"spectral":[69],"feature":[70],"vectors":[71],"without":[72],"making":[73],"use":[74],"any":[76],"discriminative":[77,89],"information.":[78],"Once":[79],"pre-training":[82],"has":[83],"designed":[84],"features,":[86],"we":[87],"perform":[88],"fine-tuning":[90],"using":[91],"backpropagation":[92],"to":[93,98],"adjust":[94],"slightly":[97],"make":[99],"them":[100],"at":[102],"predicting":[103],"probability":[105],"over":[107],"states":[109],"monophone":[111],"models.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":73},{"year":2022,"cited_by_count":91},{"year":2021,"cited_by_count":107},{"year":2020,"cited_by_count":159},{"year":2019,"cited_by_count":158},{"year":2018,"cited_by_count":198},{"year":2017,"cited_by_count":159},{"year":2016,"cited_by_count":156},{"year":2015,"cited_by_count":192},{"year":2014,"cited_by_count":175},{"year":2013,"cited_by_count":123},{"year":2012,"cited_by_count":53}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}