{"id":"https://openalex.org/W3190941125","doi":"https://doi.org/10.1587/transinf.2020bdp0005","title":"Toward Human-Friendly ASR Systems: Recovering Capitalization and Punctuation for Vietnamese Text","display_name":"Toward Human-Friendly ASR Systems: Recovering Capitalization and Punctuation for Vietnamese Text","publication_year":2021,"publication_date":"2021-07-31","ids":{"openalex":"https://openalex.org/W3190941125","doi":"https://doi.org/10.1587/transinf.2020bdp0005","mag":"3190941125"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2020bdp0005","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020bdp0005","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/8/E104.D_2020BDP0005/_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/8/E104.D_2020BDP0005/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100695332","display_name":"Thi Thu Hien Nguyen","orcid":"https://orcid.org/0000-0001-7726-3034"},"institutions":[{"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"]},{"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"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Thi Thu HIEN NGUYEN","raw_affiliation_strings":["Thai Nguyen University of Education","Vietnam Artificial Intelligence System"],"affiliations":[{"raw_affiliation_string":"Thai Nguyen University of Education","institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"]},{"raw_affiliation_string":"Vietnam Artificial Intelligence System","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044152577","display_name":"Thai Binh Nguyen","orcid":"https://orcid.org/0009-0008-8100-6338"},"institutions":[{"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"]},{"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"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thai BINH NGUYEN","raw_affiliation_strings":["Thai Nguyen University of Education","Vietnam Artificial Intelligence System"],"affiliations":[{"raw_affiliation_string":"Thai Nguyen University of Education","institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"]},{"raw_affiliation_string":"Vietnam Artificial Intelligence System","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067573637","display_name":"Pham Ngoc Phuong","orcid":"https://orcid.org/0000-0002-7741-3570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc PHUONG PHAM","raw_affiliation_strings":["Vietnam Artificial Intelligence System"],"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence System","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110936633","display_name":"Quoc Truong","orcid":"https://orcid.org/0009-0008-8098-2492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc TRUONG DO","raw_affiliation_strings":["Vietnam Artificial Intelligence System"],"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence System","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065277293","display_name":"Tu LUC LE","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu LUC LE","raw_affiliation_strings":["Office of Hanoi People's Committee"],"affiliations":[{"raw_affiliation_string":"Office of Hanoi People's Committee","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052741228","display_name":"Chi Mai Luong","orcid":"https://orcid.org/0000-0002-2559-2247"},"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":"Chi MAI LUONG","raw_affiliation_strings":["University of Science and Technology of Hanoi"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of Hanoi","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100695332"],"corresponding_institution_ids":["https://openalex.org/I4210115718","https://openalex.org/I4387154701"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54167391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E104.D","issue":"8","first_page":"1195","last_page":"1203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.8683886528015137},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.8560692667961121},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.8474231958389282},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7798845767974854},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.690967321395874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6495603322982788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.646210789680481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5391403436660767},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5208476185798645},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.502598762512207},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.479233056306839},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4631675183773041},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.14147540926933289},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13514477014541626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8683886528015137},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8560692667961121},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8474231958389282},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7798845767974854},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.690967321395874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6495603322982788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.646210789680481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391403436660767},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5208476185798645},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.502598762512207},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.479233056306839},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4631675183773041},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.14147540926933289},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13514477014541626},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2020bdp0005","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020bdp0005","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/8/E104.D_2020BDP0005/_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"}],"best_oa_location":{"id":"doi:10.1587/transinf.2020bdp0005","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020bdp0005","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E104.D/8/E104.D_2020BDP0005/_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":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3190941125.pdf","grobid_xml":"https://content.openalex.org/works/W3190941125.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W94670513","https://openalex.org/W1587490638","https://openalex.org/W2014703436","https://openalex.org/W2062752744","https://openalex.org/W2130784467","https://openalex.org/W2166116787","https://openalex.org/W2169187092","https://openalex.org/W2397041827","https://openalex.org/W2398104528","https://openalex.org/W2403334028","https://openalex.org/W2513522215","https://openalex.org/W2562621885","https://openalex.org/W2757416441","https://openalex.org/W2787556430","https://openalex.org/W2884262036","https://openalex.org/W2890448475","https://openalex.org/W2896457183","https://openalex.org/W2911304011","https://openalex.org/W2933138175","https://openalex.org/W2949271546","https://openalex.org/W2963403868","https://openalex.org/W2973071945","https://openalex.org/W2978432747","https://openalex.org/W2993229155","https://openalex.org/W3011222885","https://openalex.org/W4239753979"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W2995082385","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W2061834489","https://openalex.org/W2751906762","https://openalex.org/W3088215229","https://openalex.org/W2078793151"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,28,114,145],"is":[2,126],"a":[3],"technique":[4],"that":[5,137],"recognizes":[6],"words":[7],"and":[8,13,52,69,107,121],"sentences":[9,120],"in":[10,43,84,141],"audio":[11],"form":[12],"converts":[14],"them":[15],"into":[16],"text":[17],"sentences.":[18],"Currently,":[19],"with":[20,99,132],"the":[21,71,81,96,110,138,142,148],"advancement":[22],"of":[23,49],"deep":[24],"learning":[25],"technologies,":[26],"speech":[27,113],"has":[29],"achieved":[30],"very":[31],"satisfactory":[32],"results":[33,45,73],"close":[34],"to":[35,67,79,94,104,128],"human":[36],"abilities.":[37],"However,":[38],"there":[39],"are":[40],"still":[41],"limitations":[42],"identification":[44,72],"such":[46],"as":[47,76,78],"lack":[48],"punctuation,":[50],"capitalization,":[51],"standardized":[53],"numerical":[54],"data.":[55],"Vietnamese":[56,111,143],"also":[57],"contains":[58],"local":[59],"words,":[60],"homonyms,":[61],"etc,":[62],"which":[63],"make":[64],"it":[65,125],"difficult":[66],"read":[68],"understand":[70],"for":[74,109],"users":[75],"well":[77],"perform":[80],"next":[82],"tasks":[83],"Natural":[85],"Language":[86],"Processing":[87],"(NLP).":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"combine":[95],"transformer":[97],"decoder":[98],"conditional":[100],"random":[101],"field":[102],"(CRF)":[103],"restore":[105],"punctuation":[106],"capitalization":[108],"automatic":[112],"(ASR)":[115],"output.":[116],"By":[117],"chunking":[118],"input":[119],"merging":[122],"output":[123],"sequences,":[124],"possible":[127],"handle":[129],"longer":[130],"strings":[131],"greater":[133],"accuracy.":[134],"Experiments":[135],"show":[136],"method":[139],"proposed":[140],"post-speech":[144],"dataset":[146],"delivers":[147],"best":[149],"results.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
