{"id":"https://openalex.org/W2005708641","doi":"https://doi.org/10.1109/asru.2013.6707742","title":"Hybrid speech recognition with Deep Bidirectional LSTM","display_name":"Hybrid speech recognition with Deep Bidirectional LSTM","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2005708641","doi":"https://doi.org/10.1109/asru.2013.6707742","mag":"2005708641"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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":["Department of Computer Science, University of Toronto, Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"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/A5112445699","display_name":"Navdeep Jaitly","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":"Navdeep Jaitly","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"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/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":["Department of Computer Science, University of Toronto, Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"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":39.3549,"has_fulltext":false,"cited_by_count":1799,"citation_normalized_percentile":{"value":0.99883244,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"278"},"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":0.9988999962806702,"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":0.9972000122070312,"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":0.9135696887969971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8587218523025513},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.749768853187561},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7363592982292175},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7105141282081604},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6517077684402466},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5649511814117432},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5554653406143188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5337005257606506},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5336086750030518},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5302571654319763},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5263349413871765},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4272489845752716},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41510236263275146},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2310025990009308}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9135696887969971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587218523025513},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.749768853187561},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7363592982292175},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7105141282081604},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6517077684402466},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5649511814117432},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5554653406143188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5337005257606506},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5336086750030518},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5302571654319763},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5263349413871765},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4272489845752716},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41510236263275146},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2310025990009308},{"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/asru.2013.6707742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.5980","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.5980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/%7Egraves/asru_2013_poster.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1524333225","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/W2108677974","https://openalex.org/W2110871230","https://openalex.org/W2115730999","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2141778357","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2290318471","https://openalex.org/W4285719527","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6676315081"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W80018097","https://openalex.org/W2050397613","https://openalex.org/W2100729928","https://openalex.org/W2964207879","https://openalex.org/W2080458333","https://openalex.org/W3181208372","https://openalex.org/W1694601526"],"abstract_inverted_index":{"Deep":[0],"Bidirectional":[1],"LSTM":[2],"(DBLSTM)":[3],"recurrent":[4],"neural":[5,57],"networks":[6],"have":[7],"recently":[8],"been":[9],"shown":[10],"to":[11,34,124,137,140,143],"give":[12],"state-of-the-art":[13],"performance":[14],"on":[15,27,71,86],"the":[16,21,46,74,90,96,103,118,146],"TIMIT":[17,72],"speech":[18,40],"database.":[19],"However,":[20],"results":[22,70],"in":[23,54,98,112,148],"that":[24,63,117],"work":[25],"relied":[26],"recurrent-neural-network-specific":[28],"objective":[29],"functions,":[30],"which":[31],"are":[32],"difficult":[33],"integrate":[35],"with":[36,121],"existing":[37],"large":[38],"vocabulary":[39],"recognition":[41],"systems.":[42],"This":[43],"paper":[44],"investigates":[45],"use":[47],"of":[48,89],"DBLSTM":[49,122],"as":[50,73],"an":[51],"acoustic":[52,131],"model":[53],"a":[55,64,87,109],"standard":[56],"network-HMM":[58],"hybrid":[59,66,119],"system.":[60],"We":[61,115],"find":[62],"DBLSTM-HMM":[65],"gives":[67],"equally":[68],"good":[69],"previous":[75],"work.":[76],"It":[77],"also":[78],"outperforms":[79],"both":[80],"GMM":[81],"and":[82],"deep":[83,104],"network":[84,105],"benchmarks":[85],"subset":[88],"Wall":[91],"Street":[92],"Journal":[93],"corpus.":[94],"However":[95],"improvement":[97],"word":[99,153],"error":[100,154],"rate":[101],"over":[102],"is":[106],"modest,":[107],"despite":[108],"great":[110],"increase":[111],"framelevel":[113],"accuracy.":[114],"conclude":[116],"approach":[120],"appears":[123],"be":[125,138],"well":[126],"suited":[127],"for":[128],"tasks":[129],"where":[130],"modelling":[132],"predominates.":[133],"Further":[134],"investigation":[135],"needs":[136],"conducted":[139],"understand":[141],"how":[142],"better":[144,152],"leverage":[145],"improvements":[147],"frame-level":[149],"accuracy":[150],"towards":[151],"rates.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":130},{"year":2023,"cited_by_count":128},{"year":2022,"cited_by_count":170},{"year":2021,"cited_by_count":229},{"year":2020,"cited_by_count":250},{"year":2019,"cited_by_count":239},{"year":2018,"cited_by_count":220},{"year":2017,"cited_by_count":168},{"year":2016,"cited_by_count":98},{"year":2015,"cited_by_count":53},{"year":2014,"cited_by_count":21},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}