{"id":"https://openalex.org/W2993229155","doi":"https://doi.org/10.1109/kse.2019.8919342","title":"Recovering Capitalization for Automatic Speech Recognition of Vietnamese using Transformer and Chunk Merging","display_name":"Recovering Capitalization for Automatic Speech Recognition of Vietnamese using Transformer and Chunk Merging","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2993229155","doi":"https://doi.org/10.1109/kse.2019.8919342","mag":"2993229155"},"language":"en","primary_location":{"id":"doi:10.1109/kse.2019.8919342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"},"type":"article","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/A5102728440","display_name":"Hi\u1ec1n Nguy\u1ec5n Th\u1ecb Thu","orcid":"https://orcid.org/0009-0006-8423-9669"},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]},{"id":"https://openalex.org/I4387154701","display_name":"Thai Nguyen University Of Education","ror":"https://ror.org/044deqz63","country_code":null,"type":"education","lineage":["https://openalex.org/I4387154701"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hien Nguyen Thi Thu","raw_affiliation_strings":["Department of Mathematics, Thai Nguyen University of Education, Thai Nguyen, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Thai Nguyen University of Education, Thai Nguyen, Viet Nam","institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Binh Nguyen Thai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binh Nguyen Thai","raw_affiliation_strings":["Research Department, Vietnam Artificial Intelligence System, Ha Noi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Research Department, Vietnam Artificial Intelligence System, Ha Noi, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034816146","display_name":"Hung Nguyen Vu Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]},{"id":"https://openalex.org/I4387154701","display_name":"Thai Nguyen University Of Education","ror":"https://ror.org/044deqz63","country_code":null,"type":"education","lineage":["https://openalex.org/I4387154701"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hung Nguyen Vu Bao","raw_affiliation_strings":["Department of Mathematics, Thai Nguyen University of Education, Thai Nguyen, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Thai Nguyen University of Education, Thai Nguyen, Viet Nam","institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001197934","display_name":"Truong Do Quoc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Truong Do Quoc","raw_affiliation_strings":["Director of VAIS, Vietnam Artificial Intelligence System, Ha Noi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Director of VAIS, Vietnam Artificial Intelligence System, Ha Noi, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018070036","display_name":"Mai Chi Luong","orcid":"https://orcid.org/0009-0008-0406-864X"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Mai Luong Chi","raw_affiliation_strings":["Co-director of ICT department, University of Science and Technology of Hanoi, Ha Noi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Co-director of ICT department, University of Science and Technology of Hanoi, Ha Noi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091696309","display_name":"Huy\u1ec1n Nguy\u1ec5n Th\u1ecb Minh","orcid":null},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huyen Nguyen Thi Minh","raw_affiliation_strings":["Department of Mathematics - Mechanics and Informatics, VNU University of Science, Ha Noi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics - Mechanics and Informatics, VNU University of Science, Ha Noi, Viet Nam","institution_ids":["https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102728440"],"corresponding_institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"],"apc_list":null,"apc_paid":null,"fwci":0.7225,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79515432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9997000098228455,"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":0.9986000061035156,"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":0.8540347814559937},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7245301008224487},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6605098843574524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6563307046890259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6540603041648865},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5855411887168884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340019464492798},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.5288266539573669},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5061997771263123},{"id":"https://openalex.org/keywords/homophone","display_name":"Homophone","score":0.4341723918914795},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1139744222164154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07738536596298218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540347814559937},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7245301008224487},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6605098843574524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6563307046890259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6540603041648865},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5855411887168884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340019464492798},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.5288266539573669},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5061997771263123},{"id":"https://openalex.org/C160253069","wikidata":"https://www.wikidata.org/wiki/Q221079","display_name":"Homophone","level":2,"score":0.4341723918914795},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1139744222164154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07738536596298218},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse.2019.8919342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1571969069","https://openalex.org/W2014703436","https://openalex.org/W2062752744","https://openalex.org/W2130942839","https://openalex.org/W2144896964","https://openalex.org/W2169187092","https://openalex.org/W2407834842","https://openalex.org/W2553303224","https://openalex.org/W2884262036","https://openalex.org/W2890448475","https://openalex.org/W2963212250","https://openalex.org/W2963418779","https://openalex.org/W4297747548","https://openalex.org/W4385245566","https://openalex.org/W6654379405","https://openalex.org/W6679436768","https://openalex.org/W6714054690","https://openalex.org/W6729956949","https://openalex.org/W6739901393","https://openalex.org/W6749669830"],"related_works":["https://openalex.org/W2358775429","https://openalex.org/W1567440624","https://openalex.org/W2364211260","https://openalex.org/W1977345729","https://openalex.org/W2105439214","https://openalex.org/W2079548008","https://openalex.org/W2030399736","https://openalex.org/W1985374210","https://openalex.org/W4245032792","https://openalex.org/W3120964541"],"abstract_inverted_index":{"In":[0,97],"the":[1,29,62,127],"last":[2],"few":[3],"years,":[4],"Automatic":[5],"Speech":[6],"Recognition":[7,74],"(ASR)":[8],"systems":[9],"for":[10,42,49,107],"Vietnamese":[11,77,112],"are":[12],"utilized":[13],"in":[14,123],"various":[15],"applications":[16],"with":[17],"exceptional":[18],"results.":[19],"Nevertheless,":[20],"such":[21,27,87],"ASR":[22,78,109],"output":[23,79],"still":[24],"contains":[25],"limitations":[26],"as":[28,88],"absence":[30],"of":[31,61,111],"punctuation,":[32],"capitalization":[33],"and":[34,48,71,95,116],"standardize":[35],"numeric":[36],"data.":[37],"These":[38],"shortcomings":[39],"cause":[40],"difficulties":[41],"readers":[43],"to":[44,55,66,85,104],"understand":[45],"context":[46],"efficiently":[47],"Natural":[50],"Language":[51],"Processing":[52],"(NLP)":[53],"tasks":[54],"be":[56],"well-performed.":[57],"Capitalization":[58,106],"is":[59],"one":[60],"most":[63],"critical":[64],"factors":[65],"enhance":[67],"human":[68],"readability,":[69],"parsing,":[70],"Named":[72],"Entity":[73],"(NER).":[75],"Additionally,":[76],"has":[80],"its":[81],"own":[82],"features":[83],"comparing":[84],"English":[86],"lisp":[89],"words,":[90,92,94],"local":[91],"compound":[93],"homophone.":[96],"this":[98],"paper,":[99],"we":[100,120],"propose":[101],"a":[102],"method":[103],"Recover":[105],"long-speech":[108],"transcription":[110],"using":[113],"Transformer":[114],"models":[115],"chunk":[117],"merging.":[118],"Furthermore,":[119],"perform":[121],"decoding":[122],"parallel":[124],"while":[125],"improving":[126],"prediction":[128],"accuracy.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
