{"id":"https://openalex.org/W3007433671","doi":"https://doi.org/10.1109/asru46091.2019.9003749","title":"Transformer ASR with Contextual Block Processing","display_name":"Transformer ASR with Contextual Block Processing","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007433671","doi":"https://doi.org/10.1109/asru46091.2019.9003749","mag":"3007433671"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003749","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"middle","author":{"id":"https://openalex.org/A5084435555","display_name":"Toshiyuki Kumakura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshiyuki Kumakura","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":3.499,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.94788376,"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":"427","last_page":"433"},"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/transformer","display_name":"Transformer","score":0.7995971441268921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331920862197876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.591438889503479},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5869143605232239},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.509748637676239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4687167704105377},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46529850363731384},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.44637688994407654},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43564102053642273},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.43032175302505493},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41973087191581726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33964604139328003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3256723880767822},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12228870391845703}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7995971441268921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331920862197876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.591438889503479},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5869143605232239},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.509748637676239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4687167704105377},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46529850363731384},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.44637688994407654},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43564102053642273},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.43032175302505493},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41973087191581726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33964604139328003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3256723880767822},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12228870391845703},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003749","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2005708641","https://openalex.org/W2063224314","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2423557781","https://openalex.org/W2491408735","https://openalex.org/W2514969556","https://openalex.org/W2526425061","https://openalex.org/W2608712415","https://openalex.org/W2745439869","https://openalex.org/W2755682845","https://openalex.org/W2766219058","https://openalex.org/W2775766866","https://openalex.org/W2799800213","https://openalex.org/W2892009249","https://openalex.org/W2899771611","https://openalex.org/W2911291251","https://openalex.org/W2913718171","https://openalex.org/W2936078256","https://openalex.org/W2936123380","https://openalex.org/W2940744433","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963636093","https://openalex.org/W2964089206","https://openalex.org/W2964110616","https://openalex.org/W2964272710","https://openalex.org/W4294619417","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6728030952","https://openalex.org/W6739901393","https://openalex.org/W6750226204","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"The":[0],"Transformer":[1,27,54],"self-attention":[2],"network":[3],"has":[4,28],"recently":[5],"shown":[6],"promising":[7],"performance":[8],"as":[9],"an":[10],"alternative":[11],"to":[12,39,75,96,101,145],"recurrent":[13],"neural":[14],"networks":[15],"(RNNs)":[16],"in":[17,31],"end-to-end":[18],"(E2E)":[19],"automatic":[20],"speech":[21,119],"recognition":[22,120],"(ASR)":[23],"systems.":[24],"However,":[25],"the":[26,33,53,70,98,103,108,136,148,154],"a":[29,47,58,92],"drawback":[30],"that":[32,123],"entire":[34],"input":[35],"sequence":[36],"is":[37,143],"required":[38],"compute":[40],"self-attention.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"new":[48],"block":[49,73,127,132],"processing":[50,128,133],"method":[51,129],"for":[52],"encoder":[55],"by":[56],"introducing":[57],"context-aware":[59],"inheritance":[60,100,151],"mechanism.":[61],"An":[62],"additional":[63],"context":[64,99],"embedding":[65],"vector":[66],"handed":[67],"over":[68],"from":[69],"previously":[71],"processed":[72],"helps":[74],"encode":[76],"not":[77],"only":[78],"local":[79],"acoustic":[80],"information":[81],"but":[82],"also":[83],"global":[84,155],"linguistic,":[85],"channel,":[86],"and":[87,116],"speaker":[88],"attributes.":[89],"We":[90],"introduce":[91],"novel":[93],"mask":[94],"technique":[95],"implement":[97],"train":[102],"model":[104],"efficiently.":[105],"Evaluations":[106],"of":[107,140],"Wall":[109],"Street":[110],"Journal":[111],"(WSJ),":[112],"Librispeech,":[113],"VoxForge":[114],"Italian,":[115],"AISHELL-1":[117],"Mandarin":[118],"datasets":[121],"show":[122],"our":[124],"proposed":[125],"contextual":[126,150],"outperforms":[130],"naive":[131],"consistently.":[134],"Furthermore,":[135],"attention":[137],"weight":[138],"tendency":[139],"each":[141],"layer":[142],"analyzed":[144],"clarify":[146],"how":[147],"added":[149],"mechanism":[152],"models":[153],"information.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}