{"id":"https://openalex.org/W4206052371","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660580","title":"Multi-Encoder Sequential Attention Network for Context-Aware Speech Recognition in Japanese Dialog Conversation","display_name":"Multi-Encoder Sequential Attention Network for Context-Aware Speech Recognition in Japanese Dialog Conversation","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4206052371","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660580"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5084467777","display_name":"Nobuya Tachimori","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nobuya Tachimori","raw_affiliation_strings":["Onkyo Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Onkyo Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project (AIP), Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080776631","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0003-3492-7093"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","RIKEN, Center for Advanced Intelligence Project (AIP), Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project (AIP), Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084467777"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20104407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.9973000288009644,"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":0.8251547813415527},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7777175903320312},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7760822772979736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7536672949790955},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6194289922714233},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5900847911834717},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4247526228427887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3925628662109375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37377381324768066},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12329548597335815},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12012910842895508},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1070871353149414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251547813415527},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7777175903320312},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7760822772979736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7536672949790955},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6194289922714233},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5900847911834717},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4247526228427887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3925628662109375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37377381324768066},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12329548597335815},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12012910842895508},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1070871353149414},{"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/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/o-cocosda202152914.2021.9660580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1990005915","https://openalex.org/W2082299764","https://openalex.org/W2101346879","https://openalex.org/W2134237567","https://openalex.org/W2147768505","https://openalex.org/W2799051177","https://openalex.org/W2886025712","https://openalex.org/W2886319145","https://openalex.org/W2891534142","https://openalex.org/W2898599211","https://openalex.org/W2937649809","https://openalex.org/W2962712961","https://openalex.org/W2962943802","https://openalex.org/W2963407669","https://openalex.org/W2972430654","https://openalex.org/W2998704965","https://openalex.org/W3035629723","https://openalex.org/W3095173472","https://openalex.org/W3096798607","https://openalex.org/W4236088841","https://openalex.org/W6623517193","https://openalex.org/W6680532216","https://openalex.org/W6736780767","https://openalex.org/W6755679326"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"Japanese":[0,108],"automatic":[1],"speech":[2],"recognition":[3,144],"(ASR)":[4],"in":[5,62,99,117],"conversation":[6,98,115],"is":[7,24],"considered":[8],"challenging":[9],"and":[10,19,89,129,149],"highly":[11],"ambiguous":[12],"because":[13],"the":[14,20,28,37,40,44,56,72,83,86,90,94,100,112,153,156],"subjects":[15],"are":[16],"usually":[17],"omitted":[18],"number":[21,51],"of":[22,39,52,58,96],"homonyms":[23],"quite":[25],"large.":[26],"Since":[27],"speaker&#x0027;s":[29],"utterance":[30,42],"alone":[31],"may":[32],"not":[33],"provide":[34],"enough":[35],"information,":[36],"context":[38,81,91,116,139,154],"previous":[41],"from":[43],"dialog":[45,80,113],"partner":[46],"might":[47],"help.":[48],"A":[49],"limited":[50],"studies":[53],"have":[54,68],"addressed":[55],"idea":[57],"incorporating":[59],"dialog-context":[60],"information":[61,140],"end-to-end":[63],"ASR":[64,109,148],"tasks.":[65],"However,":[66],"these":[67],"mainly":[69],"focused":[70],"on":[71],"English":[73],"language.":[74],"Furthermore,":[75],"although":[76],"such":[77],"models":[78],"exploit":[79],"history,":[82],"decoder":[84],"handles":[85],"current":[87],"input":[88],"simultaneously,":[92],"ignoring":[93],"sequence":[95],"a":[97,107,118,124],"process.":[101],"In":[102],"this":[103],"study,":[104],"we":[105,122],"propose":[106],"that":[110,138,151],"considers":[111],"partner&#x0027;s":[114],"sequential":[119,126],"manner.":[120],"Specifically,":[121],"use":[123],"multi-encoder":[125],"attention":[127],"network":[128],"investigate":[130],"several":[131],"possible":[132],"architectures.":[133],"The":[134],"experimental":[135],"results":[136],"reveal":[137],"helps":[141],"to":[142],"improve":[143],"performance":[145],"over":[146],"standard":[147],"systems":[150],"process":[152],"at":[155],"same":[157],"time.":[158]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
