{"id":"https://openalex.org/W2143612262","doi":"https://doi.org/10.1109/icassp.2013.6638947","title":"Speech recognition with deep recurrent neural networks","display_name":"Speech recognition with deep recurrent neural networks","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2143612262","doi":"https://doi.org/10.1109/icassp.2013.6638947","mag":"2143612262"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638947","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":"conference-paper","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/A5043473089","display_name":"Alex Graves","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":"Alex Graves","raw_affiliation_strings":["University of Toronto, Toronto, ON, CA","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, CA","institution_ids":[]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","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, ON, CA","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, CA","institution_ids":[]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, 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, ON, CA","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, CA","institution_ids":[]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, 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":null,"has_fulltext":false,"cited_by_count":8858,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6645","last_page":"6649"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.9265289306640625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8239586353302002},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6790473461151123},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6582494974136353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6298375129699707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5977837443351746},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5802342891693115},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5232452750205994},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5118705630302429},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4603516757488251},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4267022907733917},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.34714406728744507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32677873969078064}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.9265289306640625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239586353302002},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6790473461151123},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6582494974136353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6298375129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5977837443351746},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5802342891693115},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5232452750205994},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5118705630302429},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4603516757488251},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4267022907733917},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34714406728744507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32677873969078064},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638947","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":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1553004968","https://openalex.org/W1828163288","https://openalex.org/W1860566644","https://openalex.org/W1964175594","https://openalex.org/W1993882792","https://openalex.org/W2047229728","https://openalex.org/W2064675550","https://openalex.org/W2077804127","https://openalex.org/W2079735306","https://openalex.org/W2101154665","https://openalex.org/W2108677974","https://openalex.org/W2110871230","https://openalex.org/W2115730999","https://openalex.org/W2117141689","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2136727248","https://openalex.org/W2141778357","https://openalex.org/W2144499799","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2167898728","https://openalex.org/W2170942820","https://openalex.org/W2184045248","https://openalex.org/W2290318471","https://openalex.org/W4285719527","https://openalex.org/W6638749077","https://openalex.org/W6676315081","https://openalex.org/W6677452488","https://openalex.org/W7053248099"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2109916967","https://openalex.org/W2340308015","https://openalex.org/W80018097","https://openalex.org/W2100729928"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1,82],"networks":[2,98],"(RNNs)":[3],"are":[4],"a":[5,125],"powerful":[6],"model":[7],"for":[8,25],"sequential":[9],"data.":[10],"End-to-end":[11],"training":[12],"methods":[13,39],"such":[14],"as":[15],"Connectionist":[16],"Temporal":[17],"Classification":[18],"make":[19],"it":[20],"possible":[21],"to":[22,138],"train":[23],"RNNs":[24,123],"sequence":[26],"labelling":[27],"problems":[28],"where":[29],"the":[30,41,86,100,132,142],"input-output":[31],"alignment":[32],"is":[33,141],"unknown.":[34],"The":[35],"combination":[36],"of":[37,89,103,129],"these":[38],"with":[40,69,99,113],"Long":[42,120],"Short-term":[43,121],"Memory":[44,122],"RNN":[45,59],"architecture":[46],"has":[47,64],"proved":[48,93],"particularly":[49],"fruitful,":[50],"delivering":[51],"state-of-the-art":[52],"results":[53,71],"in":[54,61,96],"cursive":[55],"handwriting":[56],"recognition.":[57],"However":[58],"performance":[60],"speech":[62],"recognition":[63,135],"so":[65,94],"far":[66],"been":[67],"disappointing,":[68],"better":[70],"returned":[72],"by":[73],"deep":[74,80,97,119],"feedforward":[75],"networks.":[76],"This":[77],"paper":[78],"investigates":[79],"recurrent":[81],"networks,":[83],"which":[84,137],"combine":[85],"multiple":[87],"levels":[88],"representation":[90],"that":[91,107,118],"have":[92],"effective":[95],"flexible":[101],"use":[102],"long":[104],"range":[105],"context":[106],"empowers":[108],"RNNs.":[109],"When":[110],"trained":[111],"end-to-end":[112],"suitable":[114],"regularisation,":[115],"we":[116],"find":[117],"achieve":[124],"test":[126],"set":[127],"error":[128],"17.7%":[130],"on":[131],"TIMIT":[133],"phoneme":[134],"benchmark,":[136],"our":[139],"knowledge":[140],"best":[143],"recorded":[144],"score.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":148},{"year":2025,"cited_by_count":473},{"year":2024,"cited_by_count":532},{"year":2023,"cited_by_count":639},{"year":2022,"cited_by_count":734},{"year":2021,"cited_by_count":1167},{"year":2020,"cited_by_count":1283},{"year":2019,"cited_by_count":1346},{"year":2018,"cited_by_count":1040},{"year":2017,"cited_by_count":675},{"year":2016,"cited_by_count":473},{"year":2015,"cited_by_count":243},{"year":2014,"cited_by_count":86},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}