{"id":"https://openalex.org/W4376875103","doi":"https://doi.org/10.1142/s2717554523500042","title":"Improving Few-Shot Multi-Speaker Text-to-Speech Adaptive-Based with Extracting Mel-Vector (EMV) for Vietnamese","display_name":"Improving Few-Shot Multi-Speaker Text-to-Speech Adaptive-Based with Extracting Mel-Vector (EMV) for Vietnamese","publication_year":2022,"publication_date":"2022-09-01","ids":{"openalex":"https://openalex.org/W4376875103","doi":"https://doi.org/10.1142/s2717554523500042"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554523500042","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554523500042","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-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":true,"raw_author_name":"Phuong Pham Ngoc","raw_affiliation_strings":["Thai Nguyen University, Thai Nguyen, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-7741-3570","affiliations":[{"raw_affiliation_string":"Thai Nguyen University, Thai Nguyen, Vietnam","institution_ids":["https://openalex.org/I4210115718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068095015","display_name":"Chung Tran Quang","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chung Tran Quang","raw_affiliation_strings":["AIMed Vietnam Artificial Intelligence Solutions, Ha Noi, Vietnam","Japan Advanced Institute of Science and Technology, (JAIST) Nomi, Ishikawa 923-1292, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIMed Vietnam Artificial Intelligence Solutions, Ha Noi, Vietnam","institution_ids":[]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, (JAIST) Nomi, Ishikawa 923-1292, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"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 Luong Chi","raw_affiliation_strings":["Institute of Information Technology, Vietnam Academy of Science and Technology, Ha Noi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, Vietnam Academy of Science and Technology, Ha Noi, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067573637"],"corresponding_institution_ids":["https://openalex.org/I4210115718"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18945225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"02n03","first_page":null,"last_page":null},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.7812981605529785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7622794508934021},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6368612051010132},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.53171706199646},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49870729446411133},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4977748692035675},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4496711194515228},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43648576736450195},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4225912094116211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3738722801208496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.327800452709198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812981605529785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7622794508934021},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6368612051010132},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.53171706199646},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49870729446411133},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4977748692035675},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4496711194515228},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43648576736450195},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4225912094116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3738722801208496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.327800452709198},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2717554523500042","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554523500042","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1984765460","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2587150483","https://openalex.org/W2747874407","https://openalex.org/W2791091755","https://openalex.org/W2890964092","https://openalex.org/W2892655153","https://openalex.org/W2914971466","https://openalex.org/W2916104401","https://openalex.org/W2964138190","https://openalex.org/W2964189064","https://openalex.org/W2964243274","https://openalex.org/W2993724474","https://openalex.org/W3015440759","https://openalex.org/W3015826515","https://openalex.org/W3016021263","https://openalex.org/W3016159759","https://openalex.org/W3161704465","https://openalex.org/W3162794600","https://openalex.org/W3213544594","https://openalex.org/W4205393438","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W2998781440","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Training":[0],"a":[1,83,132,157],"multi-speaker":[2,85,152],"Text-to-Speech":[3],"(TTS)":[4],"model":[5,21,51,148,154],"requires":[6],"multiple":[7],"speakers\u2019":[8],"voices":[9],"to":[10,40,61,96],"generate":[11],"an":[12,105],"average":[13,18],"speech":[14,19,92],"model.":[15],"However,":[16,57],"the":[17,32,47,50,113,138,150,171],"synthesis":[20,59,153],"will":[22,52],"be":[23],"distorted":[24],"or":[25],"averaged,":[26],"resulting":[27],"in":[28,78],"low":[29,54],"quality":[30],"if":[31],"new":[33,97,139],"speaker\u2019s":[34,140,173],"voice":[35,60],"has":[36],"too":[37],"little":[38],"data":[39],"train.":[41],"The":[42],"existing":[43],"methods":[44],"require":[45],"fine-tuning":[46,70],"model;":[48],"otherwise,":[49],"achieve":[53,62],"adaptive":[55,64],"quality.":[56],"for":[58,127],"high":[63],"quality,":[65],"at":[66],"least":[67],"thousands":[68],"of":[69,120,160,164,170],"steps":[71],"are":[72],"required.":[73],"To":[74],"solve":[75],"these":[76],"issues,":[77],"this":[79],"paper,":[80],"we":[81],"propose":[82,104],"Vietnamese":[84],"TTS":[86],"adaptive-based":[87],"technique":[88,134],"that":[89],"synthesizes":[90],"high-quality":[91],"and":[93,130,155,162],"effectively":[94],"adapts":[95],"speakers,":[98],"with":[99,110,123,166],"two":[100],"main":[101],"improvements:":[102],"(1)":[103],"Extracting":[106],"Mel-Vector":[107],"(EMV)":[108],"architecture":[109],"three":[111],"components,":[112],"Encoder\u2013Decoder\u2013Embedding":[114],"Features,":[115],"which":[116],"enables":[117],"complete":[118],"learning":[119],"speaker":[121],"features":[122],"Mel-spectrograms":[124],"as":[125],"input":[126],"few-shot":[128],"training":[129,144],"(2)":[131],"continuous-learning":[133],"called":[135],"\u201cdata-distributing\u201d":[136],"preserves":[137],"characteristics":[141],"after":[142],"many":[143],"epochs.":[145],"Our":[146],"proposed":[147],"outperformed":[149],"baseline":[151],"achieved":[156],"MOS":[158],"score":[159],"3.8/4.6":[161],"SIM":[163],"2.6/4":[165],"only":[167],"1":[168],"min":[169],"target":[172],"voice.":[174]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}