{"id":"https://openalex.org/W4386013740","doi":"https://doi.org/10.1145/3611450.3611476","title":"Multi-Feature Cross-Lingual Transfer Learning Approach for Low-Resource Vietnamese Speech Synthesis","display_name":"Multi-Feature Cross-Lingual Transfer Learning Approach for Low-Resource Vietnamese Speech Synthesis","publication_year":2023,"publication_date":"2023-07-21","ids":{"openalex":"https://openalex.org/W4386013740","doi":"https://doi.org/10.1145/3611450.3611476"},"language":"en","primary_location":{"id":"doi:10.1145/3611450.3611476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611450.3611476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","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/A5080721062","display_name":"Zhi Qiao","orcid":"https://orcid.org/0009-0006-1812-2200"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhi Qiao","raw_affiliation_strings":["Yunnan University, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119268649","display_name":"Jian Yang","orcid":"https://orcid.org/0009-0006-3138-2779"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Yunnan University, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102940790","display_name":"Zhan Wang","orcid":"https://orcid.org/0009-0000-3988-1659"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Wang","raw_affiliation_strings":["Yunnan University, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080721062"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.3444,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65606723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"180"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8304206728935242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894836068153381},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.779862642288208},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.6767087578773499},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.6649230718612671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6356983184814453},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6016230583190918},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5594926476478577},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5342369079589844},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5231332182884216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5215099453926086},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47635769844055176},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4559843838214874},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4226803481578827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14728966355323792},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.14198702573776245}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8304206728935242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894836068153381},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.779862642288208},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.6767087578773499},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.6649230718612671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6356983184814453},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6016230583190918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5594926476478577},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5342369079589844},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5231332182884216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215099453926086},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47635769844055176},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4559843838214874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4226803481578827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14728966355323792},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.14198702573776245},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3611450.3611476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611450.3611476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2036629167","display_name":null,"funder_award_id":"61961043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1927421023","https://openalex.org/W1981276685","https://openalex.org/W2168982238","https://openalex.org/W2330979245","https://openalex.org/W2610541535","https://openalex.org/W2747874407","https://openalex.org/W2964243274","https://openalex.org/W3007075806","https://openalex.org/W3016160783","https://openalex.org/W4244626788"],"related_works":["https://openalex.org/W2946856121","https://openalex.org/W2349468610","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2370805772","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W4200068392","https://openalex.org/W231741463","https://openalex.org/W301864623"],"abstract_inverted_index":{"Abstract\u2014Based":[0],"on":[1,96],"neural":[2],"network":[3],"end-to-end":[4],"speech":[5,9,30,63,174,183],"synthesis":[6,64],"systems,":[7],"high-quality":[8],"can":[10],"be":[11],"synthesized":[12,173],"when":[13],"there":[14],"is":[15,21,37],"sufficient":[16],"training":[17,118],"data.":[18],"However,":[19],"it":[20,115],"difficult":[22],"for":[23,179],"languages":[24],"with":[25,31,65,144],"small":[26],"datasets":[27],"to":[28,42,74,108,116,152,158],"synthesize":[29],"high":[32],"quality":[33,59],"and":[34,60,87,92,113,130,175],"naturalness.":[35],"Vietnamese":[36,80],"a":[38,53,104,132],"tonal":[39],"language,":[40],"belonging":[41],"the":[43,47,58,76,83,97,117,124,141,153,159,163,168,172,177],"Vietic":[44],"branch":[45],"of":[46,62,79,100,171],"Austroasiatic":[48],"language":[49],"family,":[50],"which":[51],"uses":[52],"spelling":[54],"system.":[55],"To":[56],"improve":[57,75],"naturalness":[61],"limited":[66],"dataset":[67],"resources,":[68],"we":[69,102,128],"first":[70],"use":[71,103],"transfer":[72],"learning":[73],"acoustic":[77],"model":[78,142],"by":[81],"leveraging":[82],"similarities":[84],"in":[85],"pronunciation":[86],"grammar":[88],"between":[89],"Mandarin":[90],"Chinese":[91],"Vietnamese.":[93],"Secondly,":[94],"based":[95],"prosodic":[98,110,145],"characteristics":[99],"Vietnamese,":[101],"\"speech-text\"":[105],"alignment":[106],"tool":[107],"extract":[109],"boundary":[111],"information":[112],"supplement":[114],"text":[119,181],"sequence.":[120],"Using":[121],"FastSpeech2":[122],"as":[123],"experimental":[125,137],"baseline":[126,160],"system,":[127,161],"designed":[129],"added":[131],"prosody":[133,149,164,169],"embedding":[134,165],"layer.":[135],"The":[136],"results":[138],"show":[139],"that":[140],"trained":[143],"markers":[146],"has":[147],"better":[148],"expression":[150,170],"compared":[151,157],"original":[154],"text.":[155],"Furthermore,":[156],"adding":[162],"layer":[166],"improved":[167],"eliminated":[176],"need":[178],"marked":[180],"during":[182],"synthesis.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}