{"id":"https://openalex.org/W3197587869","doi":"https://doi.org/10.21437/interspeech.2021-1020","title":"Transcribing Paralinguistic Acoustic Cues to Target Language Text in Transformer-Based Speech-to-Text Translation","display_name":"Transcribing Paralinguistic Acoustic Cues to Target Language Text in Transformer-Based Speech-to-Text Translation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197587869","doi":"https://doi.org/10.21437/interspeech.2021-1020","mag":"3197587869"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5012526423","display_name":"Hirotaka Tokuyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirotaka Tokuyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsuhito Sudoh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2262","last_page":"2266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.914900004863739,"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":0.914900004863739,"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/paralanguage","display_name":"Paralanguage","score":0.9536951780319214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7127188444137573},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6217463612556458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5155425071716309},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5131736397743225},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.46992743015289307},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4235541820526123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3643123209476471},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.26456260681152344},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1683061122894287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10362985730171204},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08670958876609802},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08286449313163757},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06960472464561462},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05484679341316223}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9536951780319214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127188444137573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6217463612556458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5155425071716309},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131736397743225},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.46992743015289307},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4235541820526123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643123209476471},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.26456260681152344},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1683061122894287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10362985730171204},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08670958876609802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08286449313163757},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06960472464561462},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05484679341316223},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1020","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3021549496","display_name":"Developing Low-Resource Multilingual Machine Speech Chain for Breaking Language Barriers","funder_award_id":"23K21681","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3044453483","https://openalex.org/W2068799119","https://openalex.org/W123774389","https://openalex.org/W3037625699"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
