{"id":"https://openalex.org/W1942035323","doi":"https://doi.org/10.21437/interspeech.2015-654","title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","display_name":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1942035323","doi":"https://doi.org/10.21437/interspeech.2015-654","mag":"1942035323"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-654","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19909910/Lu_Zhang_ET_AL_2015_A_Study_of_the_Recurrent_Neural_Network_Encoder_Decoder.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343569","display_name":"Xingxing Zhang","orcid":"https://orcid.org/0000-0003-4012-3796"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xingxing Zhang","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091175785","display_name":"Kyunghyun Cho","orcid":"https://orcid.org/0000-0003-1669-3211"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.91,"has_fulltext":true,"cited_by_count":94,"citation_normalized_percentile":{"value":0.98618109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3249","last_page":"3253"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8031368255615234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7238675951957703},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6917757987976074},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6305533647537231},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5380024909973145},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5029329657554626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45082709193229675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33436867594718933},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06486749649047852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031368255615234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7238675951957703},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6917757987976074},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6305533647537231},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5380024909973145},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5029329657554626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45082709193229675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33436867594718933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06486749649047852},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-654","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bfb84dbf-ac07-4695-8521-396819ca3fdf","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bfb84dbf-ac07-4695-8521-396819ca3fdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19909910/Lu_Zhang_ET_AL_2015_A_Study_of_the_Recurrent_Neural_Network_Encoder_Decoder.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.716.8717","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.8717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/liang_is15a.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/bfb84dbf-ac07-4695-8521-396819ca3fdf","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bfb84dbf-ac07-4695-8521-396819ca3fdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19909910/Lu_Zhang_ET_AL_2015_A_Study_of_the_Recurrent_Neural_Network_Encoder_Decoder.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1942035323.pdf","grobid_xml":"https://content.openalex.org/works/W1942035323.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1514535095","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1710082047","https://openalex.org/W1828163288","https://openalex.org/W1895577753","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1966812932","https://openalex.org/W1977690962","https://openalex.org/W1993882792","https://openalex.org/W2000200144","https://openalex.org/W2046932483","https://openalex.org/W2064675550","https://openalex.org/W2070725064","https://openalex.org/W2083393647","https://openalex.org/W2097207027","https://openalex.org/W2100772283","https://openalex.org/W2102113734","https://openalex.org/W2107878631","https://openalex.org/W2117671523","https://openalex.org/W2125838338","https://openalex.org/W2130942839","https://openalex.org/W2131342762","https://openalex.org/W2131700150","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2137347187","https://openalex.org/W2140409019","https://openalex.org/W2156615793","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2163929346","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2173629880","https://openalex.org/W2293009711","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2964308564","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W2902723393","https://openalex.org/W2385621972","https://openalex.org/W2386387936","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W2547835662"],"abstract_inverted_index":{"Deep":[0],"neural":[1,29,132,135],"networks":[2,30],"have":[3],"advanced":[4],"the":[5,38,49,88,104],"state-of-the-art":[6],"in":[7,23],"automatic":[8],"speech":[9,57,129],"recognition,":[10,58,130],"when":[11],"combined":[12],"with":[13],"hidden":[14],"Markov":[15],"models":[16],"(HMMs).":[17],"Recently":[18],"there":[19],"has":[20],"been":[21],"interest":[22],"using":[24],"systems":[25],"based":[26],"on":[27,87],"recurrent":[28,134],"(RNNs)":[31],"to":[32],"perform":[33],"sequence":[34,70,80],"modelling":[35],"directly,":[36],"without":[37],"require-ment":[39],"of":[40,65,71,81,95,99,106],"an":[41,60,107],"HMM":[42],"superstructure.":[43],"In":[44],"this":[45,85,121],"paper,":[46],"we":[47,114],"study":[48],"RNN":[50],"encoder-decoder":[51],"approach":[52,86,122],"for":[53],"large":[54],"vocabulary":[55],"end-to-end":[56,128],"whereby":[59],"encoder":[61],"transforms":[62],"a":[63,69,76,79,92],"se-quence":[64],"acoustic":[66],"vectors":[67],"into":[68],"feature":[72],"represen-tations,":[73],"from":[74],"which":[75],"decoder":[77],"recovers":[78],"words.":[82],"We":[83],"investigated":[84],"Switchboard":[89],"corpus":[90],"us-ing":[91],"training":[93],"set":[94],"around":[96],"300":[97],"hours":[98],"transcribed":[100],"audio":[101],"data.":[102],"Without":[103],"use":[105],"explicit":[108],"language":[109],"model":[110],"or":[111],"pronunciation":[112],"lexicon,":[113],"achieved":[115],"promising":[116],"recognition":[117],"accuracy,":[118],"demon-strating":[119],"that":[120],"warrants":[123],"further":[124],"investigation.":[125],"Index":[126],"Terms:":[127],"deep":[131],"net-works,":[133],"networks,":[136],"encoder-decoder.":[137],"1.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}