{"id":"https://openalex.org/W7126047154","doi":"https://doi.org/10.1109/acompa69200.2025.00020","title":"Exploring Large Language Models for Vietnamese Command Recognition in Smart Home Environments","display_name":"Exploring Large Language Models for Vietnamese Command Recognition in Smart Home Environments","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W7126047154","doi":"https://doi.org/10.1109/acompa69200.2025.00020"},"language":null,"primary_location":{"id":"doi:10.1109/acompa69200.2025.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acompa69200.2025.00020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Advanced Computing and Analytics (ACOMPA)","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/A5124188988","display_name":"Ky Nguyen Tran Gia","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ky Nguyen Tran Gia","raw_affiliation_strings":["VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146602373","display_name":"Huy Tran Quang","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huy Tran Quang","raw_affiliation_strings":["VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124251053","display_name":"Nghia Le Hoai","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nghia Le Hoai","raw_affiliation_strings":["VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124236017","display_name":"Duy Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duy Doan","raw_affiliation_strings":["VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNUHCM - University of Information Technology,Faculty of Computer Engineering,Ho ChiMinh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64637065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7774999737739563,"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":0.7774999737739563,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.02500000037252903,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.017100000753998756,"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":0.8037999868392944},{"id":"https://openalex.org/keywords/home-automation","display_name":"Home automation","score":0.5575000047683716},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5167999863624573},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.482699990272522},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3862999975681305},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3736000061035156}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8037999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599999904632568},{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acompa69200.2025.00020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acompa69200.2025.00020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Advanced Computing and Analytics (ACOMPA)","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":5,"referenced_works":["https://openalex.org/W2191779130","https://openalex.org/W2962760690","https://openalex.org/W3097777922","https://openalex.org/W4389518695","https://openalex.org/W4402111253"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"voice":[1,75],"recognition":[2,76],"techniques":[3],"have":[4],"been":[5],"ubiquitously":[6],"applied":[7],"to":[8,11,45,72,175,183],"control":[9,34,107],"systems":[10,35],"satisfy":[12],"users":[13],"with":[14,39,97,150,156,178,186],"flexibility":[15],"and":[16,92,124,163,181],"comfort,":[17],"especially":[18],"in":[19,47,81],"smart":[20,85,110],"home":[21,86,111],"application":[22,185],"where":[23],"the":[24,67,82,132,140],"interactions":[25],"are":[26,36],"often":[27],"conducted":[28],"under":[29],"series":[30],"of":[31,66,84,90,100,102,122,129,153,160,167],"commands.":[32],"However,":[33],"mostly":[37],"introduced":[38],"English":[40,51],"language,":[41],"which":[42],"leads":[43],"difficulty":[44],"deploy":[46],"countries":[48],"without":[49],"using":[50],"such":[52],"as":[53],"Vietnam.":[54],"In":[55,135],"this":[56],"work,":[57],"we":[58,137],"investigate":[59],"a":[60,74,98,116,143,151,157,164,173],"large":[61],"language":[62,180],"model":[63],"(LLM),":[64],"one":[65],"most":[68],"advanced":[69],"AI":[70],"techniques,":[71],"build":[73],"system":[77,114,141],"for":[78,109],"Vietnamese":[79,103,179],"commands":[80,108],"context":[83],"control.":[87],"A":[88],"combination":[89],"PhoWhisper":[91],"PhoBERT":[93],"models":[94],"is":[95],"fine-tuned":[96],"dataset":[99],"thousands":[101],"texts":[104],"containing":[105],"popular":[106],"devices.":[112],"The":[113],"achieves":[115],"low":[117],"Word":[118],"Error":[119],"Rate":[120],"(WER)":[121],"8.06%":[123],"an":[125],"intent":[126],"classification":[127],"accuracy":[128],"97.28%":[130],"on":[131,142],"VN-SLU":[133],"dataset.":[134],"addition,":[136],"successfully":[138],"deployed":[139],"Raspberry":[144],"Pi":[145],"5,":[146],"achieving":[147],"real-time":[148],"performance":[149],"latency":[152],"1.32":[154],"seconds":[155],"memory":[158],"footprint":[159],"4.19":[161],"GB,":[162],"computational":[165],"complexity":[166],"1.13":[168],"GFLOPs.":[169],"This":[170],"work":[171],"implicates":[172],"potential":[174],"adopt":[176],"LLM":[177],"apply":[182],"practical":[184],"limited":[187],"resources.":[188]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-01-30T00:00:00"}
