{"id":"https://openalex.org/W7140116537","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.345","title":"Vietnamese Automatic Speech Recognition: A Revisit","display_name":"Vietnamese Automatic Speech Recognition: A Revisit","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140116537","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.345"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.345","pdf_url":"https://aclanthology.org/2026.findings-eacl.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.345.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130354593","display_name":"Thi Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thi Vu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130355646","display_name":"Linh The Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linh The Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130385996","display_name":"Dat Quoc Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dat Quoc Nguyen","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25244707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6557","last_page":"6568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5644999742507935,"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":0.5644999742507935,"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":0.07320000231266022,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7771999835968018},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7278000116348267},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6100999712944031},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5321000218391418},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7771999835968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526000142097473},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7278000116348267},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4230000078678131},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3244999945163727},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.345","pdf_url":"https://aclanthology.org/2026.findings-eacl.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.345","pdf_url":"https://aclanthology.org/2026.findings-eacl.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140116537.pdf","grobid_xml":"https://content.openalex.org/works/W7140116537.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"performance":[4],"is":[5],"heavily":[6],"dependent":[7],"on":[8],"the":[9,30,72,81],"availability":[10],"of":[11,32,74,83],"large-scale,":[12],"high-quality":[13,52,95],"datasets.For":[14],"low-resource":[15],"languages,":[16],"existing":[17],"open-source":[18,59],"ASR":[19,53,108],"datasets":[20,54],"often":[21],"suffer":[22],"from":[23,55],"insufficient":[24],"quality":[25],"and":[26,42,46,71,104],"inconsistent":[27],"annotation,":[28],"hindering":[29],"development":[31],"robust":[33],"models.To":[34],"address":[35],"these":[36],"challenges,":[37],"we":[38],"propose":[39],"a":[40,93,100],"novel":[41],"generalizable":[43],"data":[44,68],"aggregation":[45],"preprocessing":[47],"pipeline":[48,61],"designed":[49],"to":[50,66,89],"construct":[51],"diverse,":[56],"potentially":[57],"noisy,":[58],"sources.Our":[60],"incorporates":[62],"rigorous":[63],"processing":[64],"steps":[65],"ensure":[67],"diversity,":[69],"balance,":[70],"inclusion":[73],"crucial":[75],"features":[76],"like":[77],"word-level":[78],"timestamps.We":[79],"demonstrate":[80],"effectiveness":[82],"our":[84],"methodology":[85],"by":[86],"applying":[87],"it":[88],"Vietnamese,":[90],"resulting":[91],"in":[92],"unified,":[94],"500-hour":[96],"dataset":[97],"that":[98],"provides":[99],"foundation":[101],"for":[102],"training":[103],"evaluating":[105],"state-of-the-art":[106],"Vietnamese":[107],"systems.":[109]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}