{"id":"https://openalex.org/W2799800213","doi":"https://doi.org/10.21437/interspeech.2018-1616","title":"Improved Training of End-to-end Attention Models for Speech Recognition","display_name":"Improved Training of End-to-end Attention Models for Speech Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2799800213","doi":"https://doi.org/10.21437/interspeech.2018-1616","mag":"2799800213"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1616","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.03294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059521407","display_name":"Albert Zeyer","orcid":"https://orcid.org/0000-0002-6655-671X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Albert Zeyer","raw_affiliation_strings":["NNAISENSE, Switzerland,","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","AppTek, USA, http://","https://nnaisense.com/","www.apptek.com/,"],"affiliations":[{"raw_affiliation_string":"NNAISENSE, Switzerland,","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek, USA, http://","institution_ids":[]},{"raw_affiliation_string":"https://nnaisense.com/","institution_ids":[]},{"raw_affiliation_string":"www.apptek.com/,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002810304","display_name":"Kazuki Irie","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kazuki Irie","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["AppTek, USA, http://","Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","www.apptek.com/,"],"affiliations":[{"raw_affiliation_string":"AppTek, USA, http://","institution_ids":[]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany,","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"www.apptek.com/,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059521407"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":37.8624,"has_fulltext":false,"cited_by_count":281,"citation_normalized_percentile":{"value":0.99765969,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"11"},"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":0.9980000257492065,"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":0.9958000183105469,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8456137180328369},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7231429815292358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717844545841217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7072339057922363},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6199902296066284},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5577782392501831},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.485058456659317},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4694235920906067},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4341506063938141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3286430835723877},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14744305610656738}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8456137180328369},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7231429815292358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717844545841217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7072339057922363},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6199902296066284},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5577782392501831},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.485058456659317},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4694235920906067},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4341506063938141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3286430835723877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14744305610656738},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1616","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.03294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.03294","pdf_url":"https://arxiv.org/pdf/1805.03294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:755694","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-236777%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"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":"Hyderabad, India 7-11 (2018). doi:10.21437/Interspeech.2018-1616","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.03294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.03294","pdf_url":"https://arxiv.org/pdf/1805.03294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1484210532","https://openalex.org/W1489125746","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1631260214","https://openalex.org/W1736701665","https://openalex.org/W1902237438","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1934041838","https://openalex.org/W1986184096","https://openalex.org/W2009150118","https://openalex.org/W2024200390","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2110871230","https://openalex.org/W2127141656","https://openalex.org/W2131968858","https://openalex.org/W2133564696","https://openalex.org/W2137550424","https://openalex.org/W2158069733","https://openalex.org/W2178654303","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2402268235","https://openalex.org/W2408504891","https://openalex.org/W2471933213","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2520160253","https://openalex.org/W2521999726","https://openalex.org/W2525778437","https://openalex.org/W2545177271","https://openalex.org/W2575312266","https://openalex.org/W2594856242","https://openalex.org/W2597757402","https://openalex.org/W2605141709","https://openalex.org/W2608712415","https://openalex.org/W2625720409","https://openalex.org/W2627092829","https://openalex.org/W2745439869","https://openalex.org/W2746192915","https://openalex.org/W2748816379","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2754219472","https://openalex.org/W2763120645","https://openalex.org/W2767601419","https://openalex.org/W2778714794","https://openalex.org/W2781384251","https://openalex.org/W2782451907","https://openalex.org/W2799923439","https://openalex.org/W2962728618","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963260202","https://openalex.org/W2963303028","https://openalex.org/W2963312585","https://openalex.org/W2963414781","https://openalex.org/W2963727906","https://openalex.org/W2963729263","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2963953073","https://openalex.org/W2964121744","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W3150637114","https://openalex.org/W3173163413","https://openalex.org/W3210141620","https://openalex.org/W4294619417","https://openalex.org/W4297818305"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W2916997151","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2949174760","https://openalex.org/W2594897229"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"attention-based":[1],"models":[2,19,108],"on":[3,24,44,49,109],"subword":[4,110],"units":[5],"allow":[6],"simple":[7],"open-vocabulary":[8],"end-to-end":[9],"speech":[10],"recognition.":[11],"In":[12,32,84,99],"this":[13],"work,":[14],"we":[15,34,87,101,115],"show":[16],"that":[17],"such":[18],"can":[20],"achieve":[21],"competitive":[22],"results":[23],"the":[25,36,45,50,97,125],"Switchboard":[26],"300h":[27],"and":[28,47,70,81],"LibriSpeech":[29],"1000h":[30],"tasks.":[31],"particular,":[33],"report":[35,116],"state-of-the-art":[37],"word":[38],"error":[39],"rates":[40],"(WER)":[41],"of":[42,54],"3.54%":[43],"dev-clean":[46],"3.82%":[48],"test-clean":[51],"evaluation":[52],"subsets":[53],"LibriSpeech.":[55],"We":[56],"introduce":[57],"a":[58,65,129],"new":[59],"pretraining":[60],"scheme":[61],"by":[62],"starting":[63],"with":[64],"high":[66],"time":[67],"reduction":[68],"factor":[69],"lowering":[71],"it":[72],"during":[73],"training,":[74],"which":[75],"is":[76],"crucial":[77],"both":[78],"for":[79],"convergence":[80],"final":[82],"performance.":[83],"some":[85],"experiments,":[86],"also":[88],"use":[89],"an":[90],"auxiliary":[91],"CTC":[92],"loss":[93],"function":[94],"to":[95,118],"help":[96],"convergence.":[98],"addition,":[100],"train":[102],"long":[103],"short-term":[104],"memory":[105],"(LSTM)":[106],"language":[107,130],"units.":[111],"By":[112],"shallow":[113],"fusion,":[114],"up":[117],"27%":[119],"relative":[120],"improvements":[121],"in":[122],"WER":[123],"over":[124],"attention":[126],"baseline":[127],"without":[128],"model.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":79},{"year":2019,"cited_by_count":83},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}