{"id":"https://openalex.org/W2913178639","doi":"https://doi.org/10.1109/slt.2018.8639629","title":"Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition","display_name":"Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913178639","doi":"https://doi.org/10.1109/slt.2018.8639629","mag":"2913178639"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"417"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.8469512462615967},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7448593974113464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7000172138214111},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.649795413017273},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5133811235427856},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5109466910362244},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48699599504470825},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.46474286913871765},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4577999413013458},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4550512731075287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42376261949539185},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3087702691555023},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0960908830165863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469512462615967},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7448593974113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7000172138214111},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.649795413017273},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5133811235427856},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5109466910362244},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48699599504470825},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.46474286913871765},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4577999413013458},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4550512731075287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42376261949539185},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3087702691555023},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0960908830165863},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1533416326","https://openalex.org/W1810943226","https://openalex.org/W1821462560","https://openalex.org/W1922655562","https://openalex.org/W2102113734","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2134797427","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2402040300","https://openalex.org/W2545177271","https://openalex.org/W2581377246","https://openalex.org/W2597757402","https://openalex.org/W2739883972","https://openalex.org/W2747909401","https://openalex.org/W2769205094","https://openalex.org/W2786018489","https://openalex.org/W2892008152","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963736842","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2963953073","https://openalex.org/W2964038834","https://openalex.org/W4297798436","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6638273328","https://openalex.org/W6638523607","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679909955","https://openalex.org/W6712847557","https://openalex.org/W6732696085","https://openalex.org/W6734588641","https://openalex.org/W6741807409","https://openalex.org/W6745801839","https://openalex.org/W6746497681","https://openalex.org/W6748161373"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W3198455051","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,118],"recognition":[3,119],"(ASR)":[4],"promises":[5],"to":[6,26,29,53],"simplify":[7],"model":[8,24,61,65],"training":[9],"and":[10,43,96],"deployment.":[11],"Most":[12],"end-to-end":[13,57],"ASR":[14],"systems":[15],"utilize":[16],"a":[17,55,63,113],"bi-directional":[18],"Long":[19],"Short-Term":[20],"Memory":[21],"(BiLSTM)":[22],"acoustic":[23,31],"due":[25],"its":[27],"ability":[28],"capture":[30],"context":[32],"from":[33,62],"the":[34,73,82,98,101,106,109],"entire":[35],"utterance.":[36],"However,":[37,70],"BiLSTM":[38,64],"models":[39],"have":[40],"high":[41],"latency":[42],"cannot":[44],"be":[45,67],"used":[46],"in":[47],"streaming":[48],"applications.":[49],"Leveraging":[50],"knowledge":[51,89],"distillation":[52,90],"train":[54],"low-latency":[56],"uni-directional":[58],"LSTM":[59],"(UniLSTM)":[60],"can":[66],"an":[68,87],"option.":[69],"it":[71],"makes":[72],"strict":[74],"assumption":[75,95],"of":[76,100,108],"shared":[77],"frame-wise":[78],"time":[79],"alignments":[80],"between":[81],"two":[83],"models.":[84],"We":[85,104],"propose":[86],"improved":[88],"algorithm":[91],"that":[92],"relaxes":[93],"this":[94],"improves":[97],"accuracy":[99],"UniLSTM":[102],"model.":[103],"confirmed":[105],"advantage":[107],"proposed":[110],"method":[111],"on":[112],"standard":[114],"English":[115],"conversational":[116],"telephone":[117],"task.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}