{"id":"https://openalex.org/W2937649809","doi":"https://doi.org/10.1109/icassp.2019.8683843","title":"Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models","display_name":"Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937649809","doi":"https://doi.org/10.1109/icassp.2019.8683843","mag":"2937649809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109336432","display_name":"Takanobu Oba","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanobu Oba","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237053","display_name":"Yushi Aono","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yushi Aono","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5661","last_page":"5665"},"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/utterance","display_name":"Utterance","score":0.9007620811462402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839272141456604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7254146337509155},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6707295775413513},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6317017078399658},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5912750363349915},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5865535736083984},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47263404726982117},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4175082743167877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41198965907096863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3970705270767212},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05709996819496155}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.9007620811462402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839272141456604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7254146337509155},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6707295775413513},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6317017078399658},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5912750363349915},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5865535736083984},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47263404726982117},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4175082743167877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41198965907096863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3970705270767212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05709996819496155},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W179875071","https://openalex.org/W1902237438","https://openalex.org/W1942035323","https://openalex.org/W1985258458","https://openalex.org/W1993378086","https://openalex.org/W2251849926","https://openalex.org/W2327501763","https://openalex.org/W2508661145","https://openalex.org/W2521999726","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2608029998","https://openalex.org/W2608712415","https://openalex.org/W2627092829","https://openalex.org/W2746192915","https://openalex.org/W2786835190","https://openalex.org/W2799800213","https://openalex.org/W2889085040","https://openalex.org/W2889374926","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962883855","https://openalex.org/W2962893195","https://openalex.org/W2963070863","https://openalex.org/W2963414781","https://openalex.org/W2963790827","https://openalex.org/W2963920996","https://openalex.org/W2964093087","https://openalex.org/W2964289193","https://openalex.org/W3022187094","https://openalex.org/W6601563604","https://openalex.org/W6607333740","https://openalex.org/W6623987585","https://openalex.org/W6629052376","https://openalex.org/W6640708543","https://openalex.org/W6676562027","https://openalex.org/W6712878229","https://openalex.org/W6728910023","https://openalex.org/W6735390525","https://openalex.org/W6736549440","https://openalex.org/W6739366949","https://openalex.org/W6742537141","https://openalex.org/W6747398299"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2947571721","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,38,86],"novel":[4],"end-to-end":[5,59,79,111,153],"automatic":[6],"speech":[7,35,137],"recognition":[8],"(ASR)":[9],"method":[10,74,95,142],"that":[11,67],"takes":[12],"into":[13],"consideration":[14],"long-range":[15,126],"sequential":[16,127],"context":[17],"information":[18],"beyond":[19,129],"utterance":[20,89,131],"boundaries.":[21,132],"In":[22],"spontaneous":[23],"ASR":[24,60,66,112,145,154],"tasks":[25,138],"such":[26],"as":[27],"those":[28],"for":[29,51,124],"discourses":[30],"and":[31,90],"conversations,":[32],"the":[33,43,46,53,72,108,130,140,150],"input":[34],"often":[36],"comprises":[37],"series":[39],"of":[40,107],"utterances.":[41,55,93],"Accordingly,":[42],"relationships":[44,84],"between":[45,85],"utterances":[47,70],"should":[48],"be":[49],"leveraged":[50],"transcribing":[52],"individual":[54],"While":[56],"most":[57,109],"previous":[58],"methods":[61],"only":[62],"focus":[63],"on":[64,134],"utterance-level":[65,152],"handles":[68],"single":[69],"independently,":[71],"proposed":[73,141],"(which":[75],"we":[76],"call":[77],"\"large-context":[78],"ASR\")":[80],"can":[81],"explicitly":[82],"utilize":[83],"current":[87],"target":[88],"all":[91],"preceding":[92],"The":[94],"is":[96,105],"modeled":[97],"by":[98],"combining":[99],"an":[100],"attention-based":[101],"encoder-decoder":[102,117],"model,":[103],"which":[104,119],"one":[106],"representative":[110],"models,":[113,118],"with":[114,149],"hierarchical":[115],"recurrent":[116],"are":[120],"effective":[121],"language":[122],"models":[123],"capturing":[125],"contexts":[128],"Experiments":[133],"Japanese":[135],"discourse":[136],"demonstrate":[139],"yields":[143],"significant":[144],"performance":[146],"improvements":[147],"compared":[148],"conventional":[151],"system.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}