{"id":"https://openalex.org/W3020420829","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295025","title":"Data Processing for Optimizing Naturalness of Vietnamese Text-to-speech System","display_name":"Data Processing for Optimizing Naturalness of Vietnamese Text-to-speech System","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3020420829","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295025","mag":"3020420829"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda50338.2020.9295025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd 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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.09607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008669300","display_name":"Viet Lam Phung","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Viet Lam Phung","raw_affiliation_strings":["Zalo Group, VNG Corporation, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Zalo Group, VNG Corporation, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017825207","display_name":"Phan Huy Kinh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Kinh Phan","raw_affiliation_strings":["Zalo Group, VNG Corporation, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Zalo Group, VNG Corporation, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088109932","display_name":"Anh Tuan Dinh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh Tuan Dinh","raw_affiliation_strings":["Zalo Group, VNG Corporation, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Zalo Group, VNG Corporation, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001160212","display_name":"Qu\u1ed1c B\u1ea3o Nguy\u1ec5n","orcid":"https://orcid.org/0000-0001-8172-8578"},"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":"Quoc Bao Nguyen","raw_affiliation_strings":["Information and Communication Technology University, Thai Nguyen University, Thai Nguyen, Vietnam"],"affiliations":[{"raw_affiliation_string":"Information and Communication Technology University, Thai Nguyen University, Thai Nguyen, Vietnam","institution_ids":["https://openalex.org/I4210115718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008669300"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52040662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9288700222969055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263967990875244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6262370944023132},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6117831468582153},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5875659584999084},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5242712497711182},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5184868574142456},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.4841955006122589},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.45120158791542053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4027253985404968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27751028537750244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09710970520973206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09227761626243591}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9288700222969055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263967990875244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6262370944023132},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6117831468582153},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5875659584999084},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5242712497711182},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5184868574142456},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.4841955006122589},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.45120158791542053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027253985404968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27751028537750244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09710970520973206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09227761626243591},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/o-cocosda50338.2020.9295025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd 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"},{"id":"pmh:oai:arXiv.org:2004.09607","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.09607","pdf_url":"https://arxiv.org/pdf/2004.09607","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3020420829","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.09607.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.09607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.09607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.09607","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.09607","pdf_url":"https://arxiv.org/pdf/2004.09607","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3020420829.pdf","grobid_xml":"https://content.openalex.org/works/W3020420829.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W40323203","https://openalex.org/W60700154","https://openalex.org/W203760253","https://openalex.org/W1586345832","https://openalex.org/W1975113979","https://openalex.org/W2114659828","https://openalex.org/W2115086266","https://openalex.org/W2137564956","https://openalex.org/W2143577772","https://openalex.org/W2250270880","https://openalex.org/W2254575701","https://openalex.org/W2289874485","https://openalex.org/W2402146185","https://openalex.org/W2519091744","https://openalex.org/W2549308614","https://openalex.org/W2560330982","https://openalex.org/W2604184139","https://openalex.org/W2787300193","https://openalex.org/W2791616807","https://openalex.org/W2892140764","https://openalex.org/W2913512413","https://openalex.org/W2925063966","https://openalex.org/W2943543019","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2992420079","https://openalex.org/W6600436803","https://openalex.org/W6601644286","https://openalex.org/W6634963458","https://openalex.org/W6677416784","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6695676441","https://openalex.org/W6712930963","https://openalex.org/W6748150159"],"related_works":["https://openalex.org/W3118227266","https://openalex.org/W3161890269","https://openalex.org/W2189470278","https://openalex.org/W2527515520","https://openalex.org/W2377466796","https://openalex.org/W3195523429","https://openalex.org/W2060855080","https://openalex.org/W2468255281","https://openalex.org/W3169170558","https://openalex.org/W2174199565","https://openalex.org/W3081565196","https://openalex.org/W2554245910","https://openalex.org/W3115948027","https://openalex.org/W2084192356","https://openalex.org/W3115632755","https://openalex.org/W2936103087","https://openalex.org/W3109498233","https://openalex.org/W3171849390","https://openalex.org/W3203313352","https://openalex.org/W2543721542"],"abstract_inverted_index":{"Abstract":[0],"End-to-end":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"has":[5],"proved":[6],"its":[7],"great":[8],"success":[9],"in":[10,22],"the":[11,46,52,81,90,114,118,121,125,134],"presence":[12],"of":[13,17,35,48,83,103,108,129,137],"a":[14,56,98],"large":[15],"amount":[16],"high-quality":[18,26],"training":[19,76],"data":[20,37,54,58,62,77,92,136],"recorded":[21],"anechoic":[23],"room":[24],"with":[25],"microphone.":[27],"Another":[28],"approach":[29],"is":[30],"to":[31,44,74,106,120],"use":[32],"available":[33],"source":[34],"found":[36,53],"like":[38],"radio":[39],"broadcast":[40],"news.":[41],"We":[42,86,111],"aim":[43],"optimize":[45,80],"naturalness":[47,82],"TTS":[49,84,96,130],"system":[50],"on":[51],"using":[55,89],"novel":[57],"processing":[59,63,91],"method.":[60],"The":[61],"method":[64],"includes":[65],"1)":[66],"utterance":[67],"selection":[68],"and":[69,127],"2)":[70],"prosodic":[71],"punctuation":[72,115],"insertion":[73,116],"prepare":[75],"which":[78],"can":[79],"systems.":[85],"showed":[87,112],"that":[88,113],"method,":[93],"an":[94],"end-to-end":[95],"achieved":[97],"mean":[99],"opinion":[100],"score":[101],"(MOS)":[102],"4.1":[104],"compared":[105],"4.3":[107],"natural":[109],"speech.":[110],"contributed":[117],"most":[119],"result.":[122],"To":[123],"facilitate":[124],"research":[126],"development":[128],"systems,":[131],"we":[132],"distributed":[133],"processed":[135],"one":[138],"speaker":[139],"at":[140],"https://forms.gle/6Hk5YkqgDxAaC2BU6.":[141]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}