{"id":"https://openalex.org/W2992420079","doi":"https://doi.org/10.1109/kse.2019.8919326","title":"A Speaker-Adaptive HMM-based Vietnamese Text-to-Speech System","display_name":"A Speaker-Adaptive HMM-based Vietnamese Text-to-Speech System","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2992420079","doi":"https://doi.org/10.1109/kse.2019.8919326","mag":"2992420079"},"language":"en","primary_location":{"id":"doi:10.1109/kse.2019.8919326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","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/A5023258175","display_name":"Duy Khanh Ninh","orcid":"https://orcid.org/0000-0003-4624-648X"},"institutions":[{"id":"https://openalex.org/I3129492623","display_name":"University of Da Nang","ror":"https://ror.org/03ecpp171","country_code":"VN","type":"education","lineage":["https://openalex.org/I3129492623"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Duy Khanh Ninh","raw_affiliation_strings":["Faculty of Information Technology, The University of Danang \u2013 University of Science and Technology, Danang, Vietnam"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, The University of Danang \u2013 University of Science and Technology, Danang, Vietnam","institution_ids":["https://openalex.org/I3129492623"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5023258175"],"corresponding_institution_ids":["https://openalex.org/I3129492623"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75934566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9812999963760376,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9528999924659729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7905148267745972},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7898856401443481},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7869200706481934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669939994812012},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5236513614654541},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41361361742019653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40845510363578796},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39735913276672363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36476826667785645},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13541489839553833}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7905148267745972},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7898856401443481},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7869200706481934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669939994812012},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5236513614654541},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41361361742019653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40845510363578796},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39735913276672363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36476826667785645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13541489839553833},{"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/kse.2019.8919326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse.2019.8919326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1980644794","https://openalex.org/W1984765460","https://openalex.org/W1984905644","https://openalex.org/W2042691334","https://openalex.org/W2050177563","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2153914468","https://openalex.org/W2182020580","https://openalex.org/W2278829316","https://openalex.org/W2398589712","https://openalex.org/W6685774320"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W4247736853","https://openalex.org/W2688184458","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,14,56,65,73,88,101,120,164,167,170],"first":[4],"attempt":[5],"in":[6],"developing":[7],"a":[8],"Vietnamese":[9,31,40,174],"HMM-based":[10],"Text-to-Speech":[11],"system":[12,26],"using":[13],"speaker-adaptive":[15,25,168],"approach.":[16],"Although":[17],"speaker-dependent":[18,78,171],"systems":[19],"have":[20,112,146],"been":[21,28],"built":[22,71,81],"widely,":[23],"no":[24],"has":[27],"developed":[29],"for":[30,173],"so":[32],"far.":[33],"We":[34],"collected":[35],"speech":[36,46,177],"data":[37],"from":[38],"several":[39],"native":[41],"speakers":[42],"and":[43,50,77,85,97,128,143,159],"employed":[44],"state-of-the-art":[45],"analysis,":[47],"model":[48,76],"training":[49],"speaker":[51],"adaptation":[52],"techniques":[53],"to":[54,63,86],"develop":[55],"system.":[57],"Besides,":[58],"we":[59],"performed":[60],"perceptual":[61],"experiments":[62],"compare":[64],"quality":[66,102,148],"of":[67,90,103,166],"speaker-adapted":[68],"(SA)":[69],"voices":[70,80,111,118,135,151],"on":[72,82,100],"average":[74],"voice":[75],"(SD)":[79],"SD":[83,117,150],"models,":[84],"confirm":[87],"effects":[89],"contextual":[91,123,139,155],"features":[92,140,156],"including":[93,157],"word":[94],"boundary":[95],"(WB)":[96],"part-of-speech":[98],"(POS)":[99],"synthetic":[104],"speech.":[105],"Evaluation":[106],"results":[107,162],"show":[108,163],"that":[109],"SA":[110,134],"significantly":[113],"higher":[114],"naturalness":[115],"than":[116,149],"when":[119],"same":[121],"limited":[122,138],"feature":[124],"set":[125],"excluding":[126,141],"WB":[127,142,158],"POS":[129,144],"was":[130],"used.":[131],"In":[132],"addition,":[133],"trained":[136,152],"with":[137,153],"still":[145],"better":[147],"full":[154],"POS.":[160],"These":[161],"robustness":[165],"over":[169],"approach":[172],"statistical":[175],"parametric":[176],"synthesis.":[178]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}