{"id":"https://openalex.org/W4206534379","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660477","title":"Simultaneous Speech-to-Speech Translation System with Transformer-Based Incremental ASR, MT, and TTS","display_name":"Simultaneous Speech-to-Speech Translation System with Transformer-Based Incremental ASR, MT, and TTS","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4206534379","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660477"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660477","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":"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/A5052080737","display_name":"Ryo Fukuda","orcid":"https://orcid.org/0009-0005-6213-3241"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Fukuda","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048192694","display_name":"Sashi Novitasari","orcid":"https://orcid.org/0000-0001-7467-5682"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sashi Novitasari","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012230189","display_name":"Yui Oka","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yui Oka","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041573401","display_name":"Yasumasa Kano","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasumasa Kano","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020010525","display_name":"Yuki Yano","orcid":"https://orcid.org/0000-0001-7706-1862"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Yano","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059938986","display_name":"Yuka Ko","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuka Ko","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012526423","display_name":"Hirotaka Tokuyama","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Tokuyama","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045126591","display_name":"Kosuke Doi","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kosuke Doi","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067528281","display_name":"Tomoya Yanagita","orcid":"https://orcid.org/0000-0001-8250-6088"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoya Yanagita","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhito Sudoh","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"186","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/speech-translation","display_name":"Speech translation","score":0.8129715919494629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878882884979248},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7600123286247253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7255522012710571},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6681972742080688},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6078107357025146},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5863444805145264},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5275803804397583},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44818827509880066},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3911358714103699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3759140968322754},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11283940076828003},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10536825656890869},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05255258083343506},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.04983973503112793}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8129715919494629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878882884979248},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7600123286247253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7255522012710571},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6681972742080688},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6078107357025146},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5863444805145264},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5275803804397583},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44818827509880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3911358714103699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759140968322754},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11283940076828003},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10536825656890869},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05255258083343506},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.04983973503112793}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660477","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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W419376470","https://openalex.org/W1902237438","https://openalex.org/W2042196737","https://openalex.org/W2101105183","https://openalex.org/W2136545725","https://openalex.org/W2161772224","https://openalex.org/W2250357346","https://openalex.org/W2529548870","https://openalex.org/W2605202026","https://openalex.org/W2747874407","https://openalex.org/W2765486990","https://openalex.org/W2887005286","https://openalex.org/W2892009249","https://openalex.org/W2903739847","https://openalex.org/W2936184970","https://openalex.org/W2951456627","https://openalex.org/W2962784628","https://openalex.org/W2963609956","https://openalex.org/W2963736842","https://openalex.org/W2972356804","https://openalex.org/W2972495969","https://openalex.org/W3034586846","https://openalex.org/W3115075512","https://openalex.org/W3142316150","https://openalex.org/W3186200218","https://openalex.org/W4385245566","https://openalex.org/W6691509046","https://openalex.org/W6736996214","https://openalex.org/W6745289305","https://openalex.org/W6784851026"],"related_works":["https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W4360995948","https://openalex.org/W596245619"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5],"English-to-Japanese":[6],"simultaneous":[7],"speech-to-speech":[8],"translation":[9,26],"(S2ST)":[10],"system.":[11],"It":[12],"has":[13],"three":[14],"Transformer-based":[15],"incremental":[16],"processing":[17],"modules":[18],"for":[19],"S2ST:":[20],"automatic":[21],"speech":[22],"recognition":[23],"(ASR),":[24],"machine":[25],"(MT),":[27],"and":[28,44],"text-to-speech":[29],"synthesis":[30],"(TTS).":[31],"We":[32],"also":[33],"evaluated":[34],"its":[35],"system-level":[36],"latency":[37,43],"in":[38],"addition":[39],"to":[40],"the":[41],"module-level":[42],"accuracy.":[45]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}