{"id":"https://openalex.org/W2964038834","doi":"https://doi.org/10.21437/interspeech.2018-2517","title":"Improved Training for Online End-to-end Speech Recognition Systems","display_name":"Improved Training for Online End-to-end Speech Recognition Systems","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2964038834","doi":"https://doi.org/10.21437/interspeech.2018-2517","mag":"2964038834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2517","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":"article","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/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Seltzer","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft AI & Research"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Microsoft AI & Research"],"affiliations":[{"raw_affiliation_string":"Microsoft AI & Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062940343"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.7486,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94674244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2913","last_page":"2917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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":0.7476373910903931},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6962544918060303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621032178401947},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5827016234397888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3525952994823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476373910903931},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6962544918060303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621032178401947},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5827016234397888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3525952994823456},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2517","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1533416326","https://openalex.org/W1736701665","https://openalex.org/W1821462560","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1965154800","https://openalex.org/W2005708641","https://openalex.org/W2102113734","https://openalex.org/W2134797427","https://openalex.org/W2136933783","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2402040300","https://openalex.org/W2521999726","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2603679025","https://openalex.org/W2606621590","https://openalex.org/W2614038158","https://openalex.org/W2711861986","https://openalex.org/W2739883972","https://openalex.org/W2892008152","https://openalex.org/W2962894366","https://openalex.org/W2962962542","https://openalex.org/W2963070863","https://openalex.org/W2963736842","https://openalex.org/W4297798436"],"related_works":["https://openalex.org/W2778699561","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W3135486970","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583","https://openalex.org/W2771275309"],"abstract_inverted_index":{"Achieving":[0],"high":[1],"accuracy":[2],"with":[3,119],"end-to-end":[4,85,92],"speech":[5,86],"recognizers":[6],"requires":[7],"careful":[8],"parameter":[9],"initialization":[10,71],"prior":[11],"to":[12,18,37,42,77,89,154],"training.Otherwise,":[13],"the":[14,34,44,95,120,140],"networks":[15],"may":[16],"fail":[17],"find":[19],"a":[20,47,62,81,98,131,145,155],"good":[21],"local":[22],"optimum.This":[23],"is":[24,41,51,57],"particularly":[25],"true":[26],"for":[27,59,97,124],"online":[28,91],"networks,":[29],"such":[30,39],"as":[31],"unidirectional":[32],"LSTMs.Currently,":[33],"best":[35],"strategy":[36,72],"train":[38],"systems":[40],"bootstrap":[43],"training":[45],"from":[46,80],"tied-triphone":[48],"system.However,":[49],"this":[50,66],"time":[52],"consuming,":[53],"and":[54,109,112,137],"more":[55],"importantly,":[56],"impossible":[58],"languages":[60],"without":[61],"high-quality":[63],"pronunciation":[64],"lexicon.In":[65],"work,":[67],"we":[68],"propose":[69],"an":[70,90],"that":[73,139],"uses":[74],"teacher-student":[75,122],"learning":[76,108,123],"transfer":[78],"knowledge":[79],"large,":[82],"well-trained,":[83],"offline":[84],"recognition":[87],"model":[88],"model,":[93],"eliminating":[94],"need":[96],"lexicon":[99],"or":[100],"any":[101],"other":[102],"linguistic":[103],"resources.We":[104],"also":[105],"explore":[106],"curriculum":[107],"label":[110],"smoothing":[111],"show":[113,138],"how":[114],"they":[115],"can":[116],"be":[117],"combined":[118],"proposed":[121,141],"further":[125],"improvements.We":[126],"evaluate":[127],"our":[128],"methods":[129],"on":[130],"Microsoft":[132],"Cortana":[133],"personal":[134],"assistant":[135],"task":[136],"method":[142],"results":[143],"in":[144,149],"19%":[146],"relative":[147],"improvement":[148],"word":[150],"error":[151],"rate":[152],"compared":[153],"randomly-initialized":[156],"baseline":[157],"system.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}