{"id":"https://openalex.org/W4205393438","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660445","title":"A Study on Neural-Network-Based Text-to-Speech Adaptation Techniques for Vietnamese","display_name":"A Study on Neural-Network-Based Text-to-Speech Adaptation Techniques for Vietnamese","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4205393438","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660445"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th 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/A5067573637","display_name":"Pham Ngoc Phuong","orcid":"https://orcid.org/0000-0002-7741-3570"},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham Ngoc Phuong","raw_affiliation_strings":["Thai Nguyen University, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thai Nguyen University, Vietnam","institution_ids":["https://openalex.org/I4210115718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068095015","display_name":"Chung Tran Quang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung Tran Quang","raw_affiliation_strings":["Vietnam Artificial Intelligence Solution, VAIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence Solution, VAIS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110936633","display_name":"Quoc Truong","orcid":"https://orcid.org/0009-0008-8098-2492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Vietnam Artificial Intelligence Solution, VAIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence Solution, VAIS","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018070036","display_name":"Mai Chi Luong","orcid":"https://orcid.org/0009-0008-0406-864X"},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Mai Chi Luong","raw_affiliation_strings":["Vietnam Academy of Science and Technology, Institute of Information Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Academy of Science and Technology, Institute of Information Technology, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58885412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.8616907000541687},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7999270558357239},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7588577270507812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6288409233093262},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6156740188598633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.574834406375885},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5344492793083191},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4964037537574768},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49615058302879333},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4357563853263855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4341471195220947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3789992332458496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3368949890136719},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07131338119506836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616907000541687},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7999270558357239},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7588577270507812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6288409233093262},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6156740188598633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.574834406375885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5344492793083191},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4964037537574768},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49615058302879333},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4357563853263855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341471195220947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3789992332458496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3368949890136719},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07131338119506836},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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-cocosda202152914.2021.9660445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th 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":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332379","display_name":"Johnson Space Center","ror":"https://ror.org/04xx4z452"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2102003408","https://openalex.org/W2346079336","https://openalex.org/W2396366106","https://openalex.org/W2402765441","https://openalex.org/W2519091744","https://openalex.org/W2766812927","https://openalex.org/W2777302760","https://openalex.org/W2808706139","https://openalex.org/W2889028433","https://openalex.org/W2892620417","https://openalex.org/W2903739847","https://openalex.org/W2923682783","https://openalex.org/W2939049741","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2969658393","https://openalex.org/W2972574864","https://openalex.org/W3004726926","https://openalex.org/W3015282541","https://openalex.org/W3015853838","https://openalex.org/W3016159759","https://openalex.org/W3024747869","https://openalex.org/W3026874504","https://openalex.org/W3038172701","https://openalex.org/W3095035471","https://openalex.org/W3095199334","https://openalex.org/W3095990227","https://openalex.org/W3128910262","https://openalex.org/W3161109662","https://openalex.org/W3168527213","https://openalex.org/W3174758275","https://openalex.org/W4287599683","https://openalex.org/W6712235671","https://openalex.org/W6713221692","https://openalex.org/W6736996214","https://openalex.org/W6758366080","https://openalex.org/W6761497924","https://openalex.org/W6763832098","https://openalex.org/W6777445600","https://openalex.org/W6777694618","https://openalex.org/W6779871621","https://openalex.org/W6785505132","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6796730497","https://openalex.org/W7043748487"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3022757400","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"One":[0,62],"of":[1,5,24,38,42,63,85,100,153,171,188],"the":[2,64,68,98,113,117,190],"main":[3],"goals":[4],"text-to-speech":[6],"adaptation":[7],"techniques":[8],"is":[9,52,71],"to":[10,66,134,144],"produce":[11],"a":[12,21,39,77,95,104,120,127,136,149,158,176,180,196],"model":[13,79,138,191],"that":[14,166],"can":[15,174,192],"generate":[16,193],"good":[17,35,159,181],"quality":[18,36],"audio":[19,194],"given":[20],"small":[22,48,151],"amount":[23,41,84,152],"training":[25,45,118],"data.":[26],"In":[27],"fact,":[28],"TTS":[29],"systems":[30],"for":[31,103,108,119],"rich-resource":[32],"languages":[33],"have":[34],"because":[37],"large":[40,83],"data,":[43,172,189],"but":[44],"models":[46],"with":[47,148,167,179,185,195],"datasets":[49],"(or":[50],"low-resources)":[51],"not":[53],"an":[54],"easy":[55],"task,":[56],"which":[57,80,131],"often":[58],"produces":[59],"low-quality":[60],"sounds.":[61],"approaches":[65],"overcome":[67],"data":[69,86,101,114,154],"limitation":[70],"fine-tuning.":[72],"However,":[73],"we":[74,111,125,173],"still":[75,156],"need":[76],"pre-trained":[78,137],"learns":[81],"from":[82,139],"in":[87],"advance.":[88],"The":[89],"paper":[90],"presents":[91],"two":[92],"contributions:":[93],"(1)":[94],"study":[96],"on":[97],"amounts":[99],"needed":[102],"traditional":[105],"fine-tuning":[106,129],"method":[107],"Vietnamese,":[109],"where":[110],"change":[112],"and":[115,141,184],"run":[116],"few":[121],"more":[122],"iterations;":[123],"(2)":[124],"present":[126],"new":[128,177],"pipeline":[130],"allows":[132],"us":[133],"borrow":[135],"English":[140],"adapt":[142],"it":[143],"any":[145],"Vietnamese":[146],"voices":[147],"very":[150],"while":[155],"maintaining":[157],"speech":[160],"synthetic":[161],"sound.":[162],"Our":[163],"experiments":[164],"show":[165],"only":[168],"4":[169],"minutes":[170,187],"synthesize":[175],"voice":[178],"similarity":[182],"score,":[183],"16":[186],"3.8":[197],"MOS":[198],"score.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
