{"id":"https://openalex.org/W4406266663","doi":"https://doi.org/10.1109/gcce62371.2024.10760868","title":"Pseudo-error Generation for Error Detection and Correction in Japanese Automatic Speech Recognition","display_name":"Pseudo-error Generation for Error Detection and Correction in Japanese Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406266663","doi":"https://doi.org/10.1109/gcce62371.2024.10760868"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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/A5018367695","display_name":"Yusei Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusei Suzuki","raw_affiliation_strings":["Shizuoka University,Hamamatsu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shizuoka University,Hamamatsu,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020888824","display_name":"Takashi Tsunakawa","orcid":"https://orcid.org/0000-0002-3880-6099"},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Tsunakawa","raw_affiliation_strings":["Shizuoka University,Hamamatsu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shizuoka University,Hamamatsu,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109009818","display_name":"Masafumi Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Nishida","raw_affiliation_strings":["Shizuoka University,Hamamatsu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shizuoka University,Hamamatsu,Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27995904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9617000222206116,"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":0.9617000222206116,"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-recognition","display_name":"Speech recognition","score":0.761317253112793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405507564544678},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.6452253460884094},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.47503307461738586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543154239654541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38585636019706726},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18429234623908997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09354528784751892}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.761317253112793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405507564544678},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.6452253460884094},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.47503307461738586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543154239654541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38585636019706726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18429234623908997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09354528784751892},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2380243770","https://openalex.org/W2377495875","https://openalex.org/W2390973415","https://openalex.org/W2074837817"],"abstract_inverted_index":{"While":[0],"the":[1,8,14,49,87],"demand":[2],"for":[3,19,29,52],"automatic":[4],"speech":[5,32],"recognition":[6,11,33],"increases,":[7],"issues":[9],"of":[10,16,70],"errors":[12],"and":[13,56,81,90],"lack":[15],"training":[17,37,53],"data":[18,38,51],"error":[20,54,96],"reduction":[21,97],"models":[22,58,72],"remain.":[23],"Therefore,":[24],"we":[25],"propose":[26],"a":[27,74,77,82],"method":[28,75],"improving":[30,95],"Japanese":[31,44],"accuracy":[34],"by":[35],"augmenting":[36],"with":[39,68],"pseudo-errors":[40],"generated":[41],"from":[42],"transcribed":[43],"dialogue":[45],"text.":[46],"We":[47],"use":[48],"augmented":[50],"detection":[55,79],"correction":[57,84],"as":[59,61],"well":[60],"investigate":[62],"their":[63],"practical":[64],"applicability.":[65],"Comparative":[66],"experiments":[67],"combinations":[69],"these":[71],"showed":[73],"combining":[76],"BERT":[78],"model":[80,85],"T5":[83],"is":[86,92],"most":[88],"effective,":[89],"augmentation":[91],"effective":[93],"in":[94],"performance.":[98]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}