{"id":"https://openalex.org/W3216100938","doi":"https://doi.org/10.1587/transinf.2021edp7014","title":"Neural Incremental Speech Recognition Toward Real-Time Machine Speech Translation","display_name":"Neural Incremental Speech Recognition Toward Real-Time Machine Speech Translation","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3216100938","doi":"https://doi.org/10.1587/transinf.2021edp7014","mag":"3216100938"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2021edp7014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/12/E104.D_2021EDP7014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/12/E104.D_2021EDP7014/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Sashi NOVITASARI","raw_affiliation_strings":["Augmented Human Communication Lab, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab, Nara Institute of Science and Technology","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"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"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":["Augmented Human Communication Lab, Nara Institute of Science and Technology","Japan Advanced Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"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/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"]},{"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":["Augmented Human Communication Lab, Nara Institute of Science and Technology","RIKEN, Center for Advanced Intelligence Project AIP"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Lab, Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048192694"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65668396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"E104.D","issue":"12","first_page":"2195","last_page":"2208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8744992017745972},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7472379207611084},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6862470507621765},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6718651056289673},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5138362050056458},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4670471251010895},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4572134017944336},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4355875551700592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40803948044776917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4006250202655792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744992017745972},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7472379207611084},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6862470507621765},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6718651056289673},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5138362050056458},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4670471251010895},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4572134017944336},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4355875551700592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40803948044776917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4006250202655792},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1587/transinf.2021edp7014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/12/E104.D_2021EDP7014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782807","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4356","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14603","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14603","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2021edp7014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/12/E104.D_2021EDP7014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2363020693","display_name":null,"funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7236939988","display_name":null,"funder_award_id":"JP21H03467","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8843746042","display_name":null,"funder_award_id":"JP21H0505","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3216100938.pdf","grobid_xml":"https://content.openalex.org/works/W3216100938.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W90894508","https://openalex.org/W121610373","https://openalex.org/W174848427","https://openalex.org/W854541894","https://openalex.org/W950853366","https://openalex.org/W1524333225","https://openalex.org/W1902237438","https://openalex.org/W2002138135","https://openalex.org/W2024490156","https://openalex.org/W2078861931","https://openalex.org/W2089629691","https://openalex.org/W2099655049","https://openalex.org/W2101105183","https://openalex.org/W2103584254","https://openalex.org/W2123301721","https://openalex.org/W2125838338","https://openalex.org/W2133564696","https://openalex.org/W2140091071","https://openalex.org/W2142416747","https://openalex.org/W2172126254","https://openalex.org/W2178654303","https://openalex.org/W2250357346","https://openalex.org/W2263232528","https://openalex.org/W2327501763","https://openalex.org/W2398009384","https://openalex.org/W2517566275","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2572461585","https://openalex.org/W2600628583","https://openalex.org/W2747874407","https://openalex.org/W2759128986","https://openalex.org/W2805490244","https://openalex.org/W2884852625","https://openalex.org/W2890197052","https://openalex.org/W2891980359","https://openalex.org/W2901607128","https://openalex.org/W2962680099","https://openalex.org/W2962742956","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963250244","https://openalex.org/W2963382687","https://openalex.org/W2963729263","https://openalex.org/W2963979492","https://openalex.org/W2964308564","https://openalex.org/W2972356804","https://openalex.org/W2972448360","https://openalex.org/W3015194534","https://openalex.org/W3015457435","https://openalex.org/W3015654466","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3034586846","https://openalex.org/W4205130185"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2338806053","https://openalex.org/W2463396630","https://openalex.org/W4385571610","https://openalex.org/W2114483840","https://openalex.org/W2010917994","https://openalex.org/W2293738010","https://openalex.org/W2100475772","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Real-time":[0],"machine":[1],"speech":[2,11,34,88,112,156],"translation":[3,174,203],"systems":[4,23],"mimic":[5],"human":[6],"interpreters":[7],"and":[8,45,83,89,121,209],"translate":[9],"incoming":[10],"from":[12,103],"a":[13,65,108,117,132,142],"source":[14],"language":[15,19],"to":[16,41,78,127,145,167,182],"the":[17,39,71,80,85,101,146,150,155,161,169,184,188,201,206,210],"target":[18],"in":[20,31,200],"real-time.":[21],"Such":[22],"can":[24],"be":[25],"achieved":[26],"by":[27],"performing":[28],"low-latency":[29],"processing":[30],"ASR":[32,60,74,106,148],"(automatic":[33],"recognition)":[35],"module":[36],"before":[37],"passing":[38],"output":[40,189],"MT":[42],"(machine":[43],"translation)":[44],"TTS":[46],"(text-to-speech":[47],"synthesis)":[48],"modules.":[49],"Although":[50],"several":[51],"studies":[52],"recently":[53],"proposed":[54],"sequence":[55],"mechanisms":[56],"for":[57,107],"neural":[58],"incremental":[59,81,151],"(ISR),":[61],"these":[62],"frameworks":[63],"have":[64,77],"more":[66],"complicated":[67],"training":[68],"mechanism":[69],"than":[70],"standard":[72],"attention-based":[73,104],"because":[75],"they":[76],"decide":[79],"step":[82],"learn":[84],"alignment":[86],"between":[87,119],"text.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,124],"propose":[95],"attention-transfer":[96],"ISR":[97,114,172,198],"(AT-ISR)":[98],"that":[99,139,194],"learns":[100],"knowledge":[102],"non-incremental":[105,147],"low":[109],"delay":[110,120,130],"end-to-end":[111,196],"recognition.":[113],"comes":[115],"with":[116,205],"trade-off":[118],"performance,":[122],"so":[123],"investigate":[125,168],"how":[126],"reduce":[128],"AT-ISR":[129,140],"without":[131],"significant":[133],"performance":[134,144],"drop.":[135],"Our":[136],"experiment":[137],"shows":[138],"achieves":[141],"comparable":[143],"when":[149],"recognition":[152],"begins":[153],"after":[154],"utterance":[157,163],"reaches":[158],"25%":[159],"of":[160,171,187],"complete":[162],"length.":[164],"Additional":[165],"experiments":[166],"effect":[170],"on":[173],"tasks":[175],"are":[176],"also":[177],"performed.":[178],"The":[179,191],"focus":[180],"is":[181],"find":[183],"optimum":[185],"granularity":[186],"unit.":[190],"results":[192],"reveal":[193],"our":[195],"subword-level":[197],"resulted":[199],"best":[202],"quality":[204],"lowest":[207,211],"WER":[208],"uncovered-word":[212],"rate.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}