{"id":"https://openalex.org/W2109886035","doi":"https://doi.org/10.1109/icassp.2016.7472618","title":"End-to-end attention-based large vocabulary speech recognition","display_name":"End-to-end attention-based large vocabulary speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2109886035","doi":"https://doi.org/10.1109/icassp.2016.7472618","mag":"2109886035"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472618","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1508.04395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010465328","display_name":"Dzmitry Bahdanau","orcid":null},"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":"Dzmitry Bahdanau","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","UNIVERSITE DE MONTREAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"UNIVERSITE DE MONTREAL","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I219388962","display_name":"University of Wroc\u0142aw","ror":"https://ror.org/00yae6e25","country_code":"PL","type":"education","lineage":["https://openalex.org/I219388962"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["CIFAR Fellow, University of Wroclaw","University of Wroclaw,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIFAR Fellow, University of Wroclaw","institution_ids":["https://openalex.org/I219388962"]},{"raw_affiliation_string":"University of Wroclaw,","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023556869","display_name":"Dmitriy Serdyuk","orcid":null},"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":"Dmitriy Serdyuk","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","UNIVERSITE DE MONTREAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"UNIVERSITE DE MONTREAL","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047130674","display_name":"Phil\u00e9mon Brakel","orcid":null},"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":"Philemon Brakel","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","UNIVERSITE DE MONTREAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"UNIVERSITE DE MONTREAL","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"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":"Yoshua Bengio","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","UNIVERSITE DE MONTREAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"UNIVERSITE DE MONTREAL","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.483,"has_fulltext":true,"cited_by_count":124,"citation_normalized_percentile":{"value":0.98791406,"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":"4945","last_page":"4949"},"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":0.9995999932289124,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8300487995147705},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8106786012649536},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7073705196380615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7067843079566956},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6845420598983765},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6243666410446167},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6190186142921448},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6161214113235474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5772104859352112},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5145394206047058},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5051279664039612},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4335746169090271},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4062865078449249},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4008547365665436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13400909304618835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300487995147705},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8106786012649536},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7073705196380615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7067843079566956},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6845420598983765},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6243666410446167},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6190186142921448},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6161214113235474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5772104859352112},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5145394206047058},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5051279664039612},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4335746169090271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4062865078449249},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4008547365665436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13400909304618835},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2016.7472618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472618","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:arXiv.org:1508.04395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04395","pdf_url":"https://arxiv.org/pdf/1508.04395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2109886035","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1508.04395.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1508.04395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1508.04395","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1508.04395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04395","pdf_url":"https://arxiv.org/pdf/1508.04395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2109886035.pdf","grobid_xml":"https://content.openalex.org/works/W2109886035.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1582482241","https://openalex.org/W1586532344","https://openalex.org/W1710082047","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W1904365287","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2113021982","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2152175008","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2162911105","https://openalex.org/W2169415433","https://openalex.org/W2949888546","https://openalex.org/W2950178297","https://openalex.org/W2950635152","https://openalex.org/W2951527505","https://openalex.org/W2952276042","https://openalex.org/W2953022181","https://openalex.org/W2953061907","https://openalex.org/W2963211739","https://openalex.org/W2964308564","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6635078382","https://openalex.org/W6636358008","https://openalex.org/W6638273328","https://openalex.org/W6638749077","https://openalex.org/W6638824847","https://openalex.org/W6639156005","https://openalex.org/W6640036494","https://openalex.org/W6640059789","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6680587008","https://openalex.org/W6682137061"],"related_works":["https://openalex.org/W2964308564","https://openalex.org/W2102113734","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2949888546","https://openalex.org/W1586532344","https://openalex.org/W2157331557","https://openalex.org/W1855892484","https://openalex.org/W1514535095","https://openalex.org/W2953022181","https://openalex.org/W1828163288","https://openalex.org/W2143612262","https://openalex.org/W1522301498","https://openalex.org/W6908809","https://openalex.org/W2963211739","https://openalex.org/W2005708641","https://openalex.org/W1710082047","https://openalex.org/W1524333225","https://openalex.org/W1902237438","https://openalex.org/W1810943226"],"abstract_inverted_index":{"Many":[0],"state-of-the-art":[1],"Large":[2],"Vocabulary":[3],"Continuous":[4],"Speech":[5],"Recognition":[6,129],"(LVCSR)":[7],"Systems":[8],"are":[9,137],"hybrids":[10],"of":[11,36,77],"neural":[12,29],"networks":[13],"and":[14,80,103,117],"Hidden":[15],"Markov":[16],"Models":[17],"(HMMs).":[18],"Recently,":[19],"more":[20],"direct":[21],"end-to-end":[22],"methods":[23],"have":[24],"been":[25],"investigated,":[26],"in":[27],"which":[28],"architectures":[30],"were":[31],"trained":[32],"to":[33,72,91,132],"model":[34,102],"sequences":[35,76],"characters":[37],"[1,2].":[38],"To":[39],"our":[40],"knowledge,":[41],"all":[42],"these":[43],"approaches":[44,136],"relied":[45],"on":[46,61],"Connectionist":[47],"Temporal":[48],"Classification":[49],"[3]":[50],"modules.":[51],"We":[52,83],"investigate":[53],"an":[54,62,99],"alternative":[55],"method":[56],"for":[57,139],"sequence":[58,122],"modelling":[59],"based":[60],"attention":[63,115],"mechanism":[64,116],"that":[65],"allows":[66],"a":[67],"Recurrent":[68],"Neural":[69],"Network":[70],"(RNN)":[71],"learn":[73],"alignments":[74],"between":[75],"input":[78],"frames":[79],"output":[81],"labels.":[82],"show":[84],"how":[85],"this":[86],"setup":[87],"can":[88],"be":[89],"applied":[90],"LVCSR":[92],"by":[93,104,109,113,118,124],"integrating":[94],"the":[95,114,120,140],"decoding":[96],"RNN":[97],"with":[98],"n-gram":[100],"language":[101],"speeding":[105],"up":[106],"its":[107],"operation":[108],"constraining":[110],"selections":[111],"made":[112],"reducing":[119],"source":[121],"lengths":[123],"pooling":[125],"information":[126],"over":[127],"time.":[128],"accuracies":[130],"similar":[131],"other":[133],"HMM-free":[134],"RNN-based":[135],"reported":[138],"Wall":[141],"Street":[142],"Journal":[143],"corpus.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":12}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}