{"id":"https://openalex.org/W4313225742","doi":"https://doi.org/10.1109/o-cocosda202257103.2022.9997947","title":"Improving Vietnamese Accent Recognition Using ASR Transfer Learning","display_name":"Improving Vietnamese Accent Recognition Using ASR Transfer Learning","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4313225742","doi":"https://doi.org/10.1109/o-cocosda202257103.2022.9997947"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202257103.2022.9997947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202257103.2022.9997947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5028029416","display_name":"Bao Thang Ta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bao Thang Ta","raw_affiliation_strings":["Viettel Cyberspace Center, Viettel Group,Vietnam","Viettel Cyberspace Center, Viettel Group, Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group,Vietnam","institution_ids":[]},{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072992021","display_name":"Xuan Dang","orcid":"https://orcid.org/0000-0002-6009-7188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Vuong Dang","raw_affiliation_strings":["Viettel Cyberspace Center, Viettel Group,Vietnam","Viettel Cyberspace Center, Viettel Group, Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group,Vietnam","institution_ids":[]},{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005248078","display_name":"Quang Tien Duong","orcid":"https://orcid.org/0000-0003-2575-5701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quang Tien Duong","raw_affiliation_strings":["Viettel Cyberspace Center, Viettel Group,Vietnam","Viettel Cyberspace Center, Viettel Group, Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group,Vietnam","institution_ids":[]},{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064078570","display_name":"Nhat Minh Le","orcid":"https://orcid.org/0000-0002-2498-9314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nhat Minh Le","raw_affiliation_strings":["Viettel Cyberspace Center, Viettel Group,Vietnam","Viettel Cyberspace Center, Viettel Group, Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group,Vietnam","institution_ids":[]},{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[{"id":"https://openalex.org/I182526193","display_name":"Thuyloi University","ror":"https://ror.org/04afshy24","country_code":"VN","type":"education","lineage":["https://openalex.org/I182526193"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["Thuyloi University,Vietnam","Thuyloi University, Vietnam"],"affiliations":[{"raw_affiliation_string":"Thuyloi University,Vietnam","institution_ids":["https://openalex.org/I182526193"]},{"raw_affiliation_string":"Thuyloi University, Vietnam","institution_ids":["https://openalex.org/I182526193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028029416"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6631,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74904746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/vietnamese","display_name":"Vietnamese","score":0.8939203023910522},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.8436273336410522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040628433227539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7461825013160706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6386620998382568},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5233539938926697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4381577968597412},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4378986358642578},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1772516369819641},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07980337738990784}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8939203023910522},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8436273336410522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040628433227539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7461825013160706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6386620998382568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5233539938926697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4381577968597412},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4378986358642578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1772516369819641},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07980337738990784},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202257103.2022.9997947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202257103.2022.9997947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2194775991","https://openalex.org/W2515121265","https://openalex.org/W2890964092","https://openalex.org/W2962898354","https://openalex.org/W2981087920","https://openalex.org/W3013562487","https://openalex.org/W3023579893","https://openalex.org/W3030437843","https://openalex.org/W3044481399","https://openalex.org/W3097777922","https://openalex.org/W3160475509","https://openalex.org/W3161674998","https://openalex.org/W3197530164","https://openalex.org/W3197813307","https://openalex.org/W3200084433","https://openalex.org/W4205262966","https://openalex.org/W4205509257","https://openalex.org/W4292002651","https://openalex.org/W4312321798","https://openalex.org/W4312944707","https://openalex.org/W4313033445","https://openalex.org/W6753010206","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W2291461084","https://openalex.org/W2050882094","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W3042674643","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"Accent":[0],"Recognition":[1],"(AR)":[2],"is":[3,13],"a":[4,22,54,94,102],"critical":[5],"task":[6],"in":[7,15,83],"voice-controlled":[8,17],"systems.":[9],"If":[10],"accent":[11,35,64],"information":[12,81],"known":[14],"advance,":[16],"systems":[18,74],"can":[19],"switch":[20],"to":[21,26,85],"suitable":[23],"accent-specific":[24],"mode":[25],"improve":[27,86],"their":[28],"performance":[29],"and":[30,79],"user":[31],"experience.":[32],"However,":[33],"available":[34,71],"datasets,":[36],"especially":[37],"Vietnamese,":[38],"are":[39],"relatively":[40],"small,":[41],"making":[42],"AR":[43,112],"very":[44],"challenging.":[45],"To":[46],"deal":[47],"with":[48],"these":[49],"drawbacks,":[50],"this":[51],"paper":[52],"proposes":[53],"transfer":[55],"learning":[56],"method":[57],"using":[58],"pretrained":[59],"ASR":[60,84],"models":[61],"for":[62],"Vietnamese":[63,95,111],"recognition.":[65],"This":[66],"helps":[67],"the":[68,106],"system":[69,108],"utilize":[70],"speech":[72],"recognition":[73],"while":[75],"capturing":[76],"implicit":[77],"linguistic":[78],"phonetic":[80],"learned":[82],"its":[87],"performance.":[88],"Several":[89],"experiments":[90],"were":[91],"conducted":[92],"on":[93],"8kHz":[96],"telephone":[97],"call":[98],"dataset,":[99],"which":[100],"showed":[101],"significant":[103],"improvement":[104],"of":[105],"proposed":[107],"over":[109],"existing":[110],"models.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
