{"id":"https://openalex.org/W2608712415","doi":"https://doi.org/10.1109/icassp.2016.7472641","title":"On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition","display_name":"On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2608712415","doi":"https://doi.org/10.1109/icassp.2016.7472641","mag":"2608712415"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/c2307a55-be29-4c92-89d7-05519e874012","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":[{"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":true,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Cognition and Computation, University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Cognition and Computation, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110383860","display_name":"Steve Renais","orcid":null},"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":"Steve Renais","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, Edinburgh, GB"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, Edinburgh, GB","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101607148"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":36.8486,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99730765,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9986000061035156,"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":0.9970999956130981,"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":0.8197367191314697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7398345470428467},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7360814809799194},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6841657161712646},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6584835648536682},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6226000785827637},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6137439608573914},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5381560921669006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5056881904602051},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4915805757045746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47987309098243713},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46910032629966736},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44644027948379517},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42459022998809814},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.42124512791633606},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37014269828796387},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16468548774719238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197367191314697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7398345470428467},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7360814809799194},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6841657161712646},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6584835648536682},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6226000785827637},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6137439608573914},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5381560921669006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5056881904602051},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4915805757045746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47987309098243713},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46910032629966736},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44644027948379517},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42459022998809814},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.42124512791633606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37014269828796387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16468548774719238},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7472641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c2307a55-be29-4c92-89d7-05519e874012","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c2307a55-be29-4c92-89d7-05519e874012","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Zhang, X & Renals, S 2016, On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5060-5064, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472641","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c2307a55-be29-4c92-89d7-05519e874012","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/c2307a55-be29-4c92-89d7-05519e874012","pdf_url":null,"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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/c2307a55-be29-4c92-89d7-05519e874012","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c2307a55-be29-4c92-89d7-05519e874012","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Zhang, X & Renals, S 2016, On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5060-5064, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472641","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W811578723","https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W1984541135","https://openalex.org/W1987238397","https://openalex.org/W1993409002","https://openalex.org/W1995562189","https://openalex.org/W2079623482","https://openalex.org/W2094147890","https://openalex.org/W2102113734","https://openalex.org/W2108563286","https://openalex.org/W2130942839","https://openalex.org/W2131342762","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2134800885","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2293634267","https://openalex.org/W2293858598","https://openalex.org/W2403195671","https://openalex.org/W2950178297","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963920996","https://openalex.org/W2964308564","https://openalex.org/W6600284362","https://openalex.org/W6629052376","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6639156005","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6676562027","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6679855610","https://openalex.org/W6696934422","https://openalex.org/W6713280142"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2495256954","https://openalex.org/W2950022897","https://openalex.org/W1566315437","https://openalex.org/W2890297197","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2101697354"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"an":[4],"increasing":[5],"interest":[6],"in":[7,26,134],"end-to-end":[8,85],"speech":[9,86],"recognition":[10,106,170],"using":[11,130,152],"neural":[12,33],"networks,":[13],"with":[14,113],"no":[15],"reliance":[16],"on":[17,79,148],"hidden":[18],"Markov":[19],"models":[20],"(HMMs)":[21],"for":[22,82],"sequence":[23,42,44,56],"modelling":[24],"as":[25],"the":[27,54,65,68,105,111,135,139,149,174,178],"standard":[28],"hybrid":[29,179],"framework.":[30],"The":[31],"recurrent":[32,119,132],"network":[34],"(RNN)":[35],"encoderdecoder":[36],"is":[37],"such":[38],"a":[39,58,91,153],"model,":[40],"performing":[41],"to":[43,177],"mapping":[45],"without":[46],"any":[47],"predefined":[48],"alignment.":[49],"This":[50],"model":[51,81],"first":[52,89],"transforms":[53],"input":[55],"into":[57],"fixed":[59],"length":[60],"vector":[61],"representation,":[62],"from":[63],"which":[64],"decoder":[66,112],"recovers":[67],"output":[69],"sequence.":[70],"In":[71],"this":[72,80],"paper,":[73],"we":[74,127,165],"extend":[75,110],"our":[76],"previous":[77],"work":[78],"large":[83],"vocabulary":[84],"recognition.":[87],"We":[88,108],"present":[90],"more":[92],"effective":[93],"stochastic":[94],"gradient":[95],"decent":[96],"(SGD)":[97],"learning":[98],"rate":[99],"schedule":[100],"that":[101,121,129],"can":[102,137],"significantly":[103,168],"improve":[104],"accuracy.":[107],"then":[109],"long":[114],"memory":[115],"by":[116],"introducing":[117],"another":[118],"layer":[120],"performs":[122],"implicit":[123],"language":[124],"modelling.":[125],"Finally,":[126],"demonstrate":[128],"multiple":[131],"layers":[133],"encoder":[136],"reduce":[138],"word":[140],"error":[141],"rate.":[142],"Our":[143],"experiments":[144],"were":[145],"carried":[146],"out":[147],"Switchboard":[150],"corpus":[151],"training":[154],"set":[155],"of":[156,160],"around":[157],"300":[158],"hours":[159],"transcribed":[161],"audio":[162],"data,":[163],"and":[164],"have":[166],"achieved":[167],"higher":[169],"accuracy,":[171],"thereby":[172],"reduced":[173],"gap":[175],"compared":[176],"baseline.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}