{"id":"https://openalex.org/W4388821323","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317128","title":"Transformer-based Automatic Speech Recognition of Simultaneous Interpretation with Auxiliary Input of Source Language Text","display_name":"Transformer-based Automatic Speech Recognition of Simultaneous Interpretation with Auxiliary Input of Source Language Text","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821323","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317128"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5016104507","display_name":"Shuta Taniguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuta Taniguchi","raw_affiliation_strings":["Doshisha University,Japan","Doshisha University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University,Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103984126","display_name":"Tsuneo Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuneo Kato","raw_affiliation_strings":["Doshisha University,Japan","Doshisha University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University,Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038864467","display_name":"Akihiro Tamura","orcid":"https://orcid.org/0000-0002-9112-7976"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Tamura","raw_affiliation_strings":["Doshisha University,Japan","Doshisha University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University,Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013983600","display_name":"Keiji Yasuda","orcid":"https://orcid.org/0000-0001-6569-5999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiji Yasuda","raw_affiliation_strings":["Mindword, Inc.,Japan","Mindword, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mindword, Inc.,Japan","institution_ids":[]},{"raw_affiliation_string":"Mindword, Inc., Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":"1857","last_page":"1861"},"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/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.8105576038360596},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7013758420944214},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6784213781356812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6245864629745483},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.5975596904754639},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5696978569030762},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5621300339698792},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5393244028091431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520828127861023},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14516490697860718},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09932318329811096},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09095814824104309},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06992566585540771},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0643174946308136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105576038360596},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7013758420944214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6784213781356812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6245864629745483},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.5975596904754639},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5696978569030762},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5621300339698792},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5393244028091431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520828127861023},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14516490697860718},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09932318329811096},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09095814824104309},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06992566585540771},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0643174946308136},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W620750443","https://openalex.org/W2096391593","https://openalex.org/W2184188583","https://openalex.org/W2619383789","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963378435","https://openalex.org/W2964012862","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2973132140","https://openalex.org/W2986148666","https://openalex.org/W3007589762","https://openalex.org/W3088950396","https://openalex.org/W3092085609","https://openalex.org/W3143320354","https://openalex.org/W4296068599","https://openalex.org/W4296068787","https://openalex.org/W4297841886","https://openalex.org/W4385245566","https://openalex.org/W6619549847","https://openalex.org/W6686207219","https://openalex.org/W6739901393","https://openalex.org/W6766904570","https://openalex.org/W6767279747"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3094871513","https://openalex.org/W3198458223","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,86,111],"recognition":[2],"(ASR)":[3],"of":[4,52,65,77,85,102,107,133],"simultaneous":[5,22,34,71,103],"interpretation":[6,23,72,104],"is":[7],"challenging":[8],"due":[9],"to":[10,123],"disfluencies":[11],"such":[12],"as":[13,112],"hesitations,":[14],"filled":[15,120,157,166],"pauses,":[16],"interruptions,":[17],"and":[18,73,94,126,155],"self-repairs.":[19],"Meanwhile,":[20],"the":[21,37,75,78,96,108,113,124,128,131,140,152,156,161,165,175],"sometimes":[24],"accompanies":[25],"source":[26,38,42,53,66,109],"language":[27,39,43,54,67,110],"text.":[28,40],"In":[29,89],"particular,":[30],"training":[31],"materials":[32],"for":[33,69],"interpreters":[35],"have":[36],"The":[41,143],"text":[44,68],"can":[45],"also":[46,117],"be":[47],"considered":[48],"an":[49],"ideal":[50],"transcription":[51,106],"speech.":[55],"Previously,":[56],"we":[57,92],"proposed":[58,97],"a":[59,100,119,134],"Transformer-based":[60],"ASR":[61,125],"with":[62,105,139],"auxiliary":[63,114,141,153,176],"input":[64,154],"transcribing":[70],"verified":[74],"effectiveness":[76],"model":[79,98,122,168],"structure":[80],"by":[81,150,164,174],"using":[82,99],"large-scale":[83],"corpora":[84],"translation":[87],"(ST).":[88],"this":[90],"study,":[91],"fine-tuned":[93],"evaluated":[95],"corpus":[101],"input.":[115,142,177],"We":[116],"added":[118],"pause":[121,158,167],"compared":[127],"effect":[129],"on":[130],"reduction":[132,162],"word":[135],"error":[136],"rate":[137],"(WER)":[138],"experimental":[144],"results":[145],"showed":[146],"significant":[147],"WER":[148],"reductions":[149],"both":[151],"model,":[159],"though":[160],"made":[163,173],"was":[169],"greater":[170],"than":[171],"that":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}