{"id":"https://openalex.org/W3148654612","doi":"https://doi.org/10.1109/slt48900.2021.9383517","title":"Streaming Transformer Asr With Blockwise Synchronous Beam Search","display_name":"Streaming Transformer Asr With Blockwise Synchronous Beam Search","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148654612","doi":"https://doi.org/10.1109/slt48900.2021.9383517","mag":"3148654612"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7146,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96931375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"29"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.7357319593429565},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7038546800613403},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.6794217824935913},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6064023971557617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.565514087677002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4298713207244873},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.421084463596344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3228447139263153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27337828278541565},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.20251280069351196},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.17960235476493835},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09100878238677979},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08942291140556335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357319593429565},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7038546800613403},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.6794217824935913},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6064023971557617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.565514087677002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298713207244873},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.421084463596344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3228447139263153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27337828278541565},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.20251280069351196},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17960235476493835},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09100878238677979},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08942291140556335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1821462560","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2178654303","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2766219058","https://openalex.org/W2802023636","https://openalex.org/W2911291251","https://openalex.org/W2913718171","https://openalex.org/W2936078256","https://openalex.org/W2936774411","https://openalex.org/W2940744433","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963864497","https://openalex.org/W2964089206","https://openalex.org/W2964110616","https://openalex.org/W2964272710","https://openalex.org/W2972439411","https://openalex.org/W2972780808","https://openalex.org/W2972818416","https://openalex.org/W2976556660","https://openalex.org/W2981696585","https://openalex.org/W3007328579","https://openalex.org/W3007433671","https://openalex.org/W3007528493","https://openalex.org/W3015190365","https://openalex.org/W3015457435","https://openalex.org/W3015654466","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3016167541","https://openalex.org/W3021469861","https://openalex.org/W3025165719","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W4294619417","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6638523607","https://openalex.org/W6685711979","https://openalex.org/W6687566353","https://openalex.org/W6712847557","https://openalex.org/W6739901393","https://openalex.org/W6747158283","https://openalex.org/W6747398299","https://openalex.org/W6750226204","https://openalex.org/W6760966419","https://openalex.org/W6761628794","https://openalex.org/W6769647859","https://openalex.org/W6771291481","https://openalex.org/W6775822104"],"related_works":["https://openalex.org/W4386269615","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4390091683","https://openalex.org/W4205302943","https://openalex.org/W2100233978","https://openalex.org/W2204575588","https://openalex.org/W3156736277","https://openalex.org/W2119949815"],"abstract_inverted_index":{"The":[0],"Transformer":[1,24,65,121,177],"self-attention":[2,39],"network":[3],"has":[4,25],"shown":[5],"promising":[6],"performance":[7,170],"as":[8],"an":[9],"alternative":[10],"to":[11,36,61,148,171],"recurrent":[12],"neural":[13],"networks":[14],"in":[15,28,100,159,179],"end-to-end":[16],"(E2E)":[17],"automatic":[18],"speech":[19],"recognition":[20],"(ASR)":[21],"systems.":[22],"However,":[23],"a":[26,48,78,84],"drawback":[27],"that":[29,117,143],"the":[30,68,95,101,105,118,135,150,154],"entire":[31],"input":[32],"sequence":[33],"is":[34,91],"required":[35],"compute":[37],"both":[38],"and":[40,97,107,112,153,174],"source-target":[41],"attention.":[42],"In":[43,67],"this":[44],"paper,":[45],"we":[46],"propose":[47],"novel":[49],"blockwise":[50,57],"synchronous":[51],"beam":[52,69],"search":[53],"algorithm":[54,122],"based":[55,93],"on":[56,94],"processing":[58],"of":[59,87,104],"encoder":[60],"perform":[62],"streaming":[63,120,145,163],"E2E":[64],"ASR.":[66],"search,":[70],"encoded":[71],"feature":[72],"blocks":[73],"are":[74],"synchronously":[75],"aligned":[76],"using":[77,134],"block":[79],"boundary":[80],"detection":[81],"technique,":[82],"where":[83],"reliability":[85],"score":[86],"each":[88],"predicted":[89],"hypothesis":[90],"evaluated":[92],"end-of-sequence":[96],"repeated":[98],"tokens":[99],"hypothesis.":[102],"Evaluations":[103],"HKUST":[106],"AISHELL-1":[108],"Mandarin,":[109],"LibriSpeech":[110],"English,":[111],"CSJ":[113],"Japanese":[114],"tasks":[115,181],"show":[116],"proposed":[119],"outperforms":[123],"conventional":[124],"online":[125],"approaches,":[126],"including":[127],"monotonic":[128],"chunkwise":[129],"attention":[130],"(MoChA),":[131],"especially":[132],"when":[133],"knowledge":[136],"distillation":[137],"technique.":[138],"An":[139],"ablation":[140],"study":[141],"indicates":[142],"our":[144],"approach":[146],"contributes":[147,157],"reducing":[149],"response":[151],"time,":[152],"repetition":[155],"criterion":[156],"significantly":[158],"certain":[160],"tasks.":[161],"Our":[162],"ASR":[164],"models":[165,173],"achieve":[166],"comparable":[167],"or":[168],"superior":[169],"batch":[172],"other":[175],"streaming-based":[176],"methods":[178],"all":[180],"considered.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}