{"id":"https://openalex.org/W2946097327","doi":"https://doi.org/10.1109/rivf.2019.8713758","title":"An End-to-End Model for Vietnamese Speech Recognition","display_name":"An End-to-End Model for Vietnamese Speech Recognition","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2946097327","doi":"https://doi.org/10.1109/rivf.2019.8713758","mag":"2946097327"},"language":"en","primary_location":{"id":"doi:10.1109/rivf.2019.8713758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","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":null,"display_name":"Van Huy Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Van Huy Nguyen","raw_affiliation_strings":["FPT Technology Research Institute, Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT Technology Research Institute, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I109689652"],"apc_list":null,"apc_paid":null,"fwci":0.5781,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75178919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1609","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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.8971399068832397},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.782554566860199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726920247077942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7522581219673157},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6462554931640625},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5011935234069824},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46569833159446716},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44958001375198364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.448625385761261},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4478600025177002},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38298824429512024}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8971399068832397},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.782554566860199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726920247077942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7522581219673157},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6462554931640625},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5011935234069824},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46569833159446716},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44958001375198364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448625385761261},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4478600025177002},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38298824429512024},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf.2019.8713758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1855892484","https://openalex.org/W2064675550","https://openalex.org/W2085628288","https://openalex.org/W2087395764","https://openalex.org/W2102113734","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2128212935","https://openalex.org/W2193413348","https://openalex.org/W2216396205","https://openalex.org/W2290689761","https://openalex.org/W2402146185","https://openalex.org/W2520160253","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2980286501","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6712930963","https://openalex.org/W6727336983","https://openalex.org/W6746892368","https://openalex.org/W6768798221"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W3126788496","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2916997151","https://openalex.org/W3198455051"],"abstract_inverted_index":{"This":[0],"paper":[1,42],"presents":[2,44],"an":[3],"approach":[4],"of":[5,86,100],"End-to-End":[6,28],"model":[7],"based":[8,50,75],"on":[9,51],"Long":[10],"Short-Term":[11],"Memory":[12],"(LSTM)":[13],"and":[14,121],"Time":[15],"Delay":[16],"Deep":[17],"Neural":[18],"Network":[19],"(TDNN)":[20],"models":[21,77,82],"for":[22,61,89,103,131],"Vietnamese":[23,27,52,90,132],"speech":[24,91],"recognition.":[25],"Two":[26],"architectures":[29],"using":[30,115],"Connectionist":[31],"Temporal":[32],"Classification":[33],"(CTC)":[34],"as":[35],"the":[36,45,58,95,118,122,129],"loss":[37],"function":[38],"are":[39,78,125],"proposed.":[40],"The":[41,69],"also":[43],"method":[46],"to":[47,56,80,112,127],"construct":[48],"phonesets":[49],"characters":[53],"or":[54],"tonemes":[55],"produce":[57],"label":[59],"sequence":[60],"any":[62],"given":[63],"transcription":[64],"when":[65],"applying":[66],"CTC":[67,74],"model.":[68],"experimental":[70],"results":[71],"showed":[72],"that":[73],"End-To-End":[76],"competitive":[79],"traditional":[81,116],"with":[83],"only":[84],"5%":[85],"WER":[87],"worse":[88],"recognition":[92],"(SR),":[93],"but":[94],"advantage":[96],"is":[97,110],"no":[98],"requirement":[99],"forced":[101],"alignment":[102],"training":[104],"acoustic":[105],"models.":[106],"In":[107],"addition,":[108],"it":[109],"similar":[111],"proposed":[113],"studies":[114],"models,":[117],"tone":[119],"information":[120],"toneme":[123],"set":[124],"solutions":[126],"optimize":[128],"performance":[130],"SR.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}