{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:10:23Z","timestamp":1776121823019,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61961043"],"award-info":[{"award-number":["61961043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2020AAA0107901"],"award-info":[{"award-number":["2020AAA0107901"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,21]]},"DOI":"10.1145\/3611450.3611476","type":"proceedings-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T01:59:46Z","timestamp":1692583186000},"page":"175-180","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Feature Cross-Lingual Transfer Learning Approach for Low-Resource Vietnamese Speech Synthesis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1812-2200","authenticated-orcid":false,"given":"Zhi","family":"Qiao","sequence":"first","affiliation":[{"name":"Yunnan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3138-2779","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Yunnan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3988-1659","authenticated-orcid":false,"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Yunnan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"STANTON D","author":"WANG Y","year":"2017","unstructured":"WANG Y , SKERRY-RYAN R J , STANTON D , Tacotron : Towards End-to-End Speech Synthesis [J]. 2017 . WANG Y, SKERRY-RYAN R J, STANTON D, Tacotron: Towards End-to-End Speech Synthesis [J]. 2017."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_3_1","volume-title":"TAN X","author":"REN Y","year":"2019","unstructured":"REN Y , RUAN Y , TAN X , Fastspeech : Fast, robust and controllable text to speech [J]. Advances in neural information processing systems, 2019 , 32. REN Y, RUAN Y, TAN X, Fastspeech: Fast, robust and controllable text to speech [J]. Advances in neural information processing systems, 2019, 32."},{"key":"e_1_3_2_1_4_1","volume-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech [J]. arXiv preprint arXiv:200604558","author":"REN Y","year":"2020","unstructured":"REN Y , HU C , TAN X , Fastspeech 2: Fast and high-quality end-to-end text to speech [J]. arXiv preprint arXiv:200604558 , 2020 . REN Y, HU C, TAN X, Fastspeech 2: Fast and high-quality end-to-end text to speech [J]. arXiv preprint arXiv:200604558, 2020."},{"key":"e_1_3_2_1_5_1","volume-title":"A survey on neural speech synthesis [J]. arXiv preprint arXiv:210615561","author":"TAN X","year":"2021","unstructured":"TAN X , QIN T , SOONG F , A survey on neural speech synthesis [J]. arXiv preprint arXiv:210615561 , 2021 . TAN X, QIN T, SOONG F, A survey on neural speech synthesis [J]. arXiv preprint arXiv:210615561, 2021."},{"key":"e_1_3_2_1_6_1","volume-title":"Columbia University Press","year":"2012","unstructured":"Sources of Vietnamese tradition[M]. Columbia University Press , 2012 . Sources of Vietnamese tradition[M]. Columbia University Press, 2012."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139021210"},{"key":"e_1_3_2_1_8_1","volume-title":"A survey of transfer learning [J]. Journal of Big data","author":"WEISS K","year":"2016","unstructured":"WEISS K , KHOSHGOFTAAR T M , WANG D. A survey of transfer learning [J]. Journal of Big data , 2016 , 3(1): 1-40. WEISS K, KHOSHGOFTAAR T M, WANG D. A survey of transfer learning [J]. Journal of Big data, 2016, 3(1): 1-40."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"e_1_3_2_1_10_1","volume-title":"Joint-sequence models for grapheme-to-phoneme conversion [J]. Speech communication","author":"BISANI M","year":"2008","unstructured":"BISANI M , NEY H. Joint-sequence models for grapheme-to-phoneme conversion [J]. Speech communication , 2008 , 50(5): 434-51. BISANI M, NEY H. Joint-sequence models for grapheme-to-phoneme conversion [J]. Speech communication, 2008, 50(5): 434-51."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.7575\/aiac.ijels.v.5n.2p.9"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941031"},{"key":"e_1_3_2_1_13_1","volume-title":"Visual prosody: Facial movements accompanying speech","author":"GRAF H P","year":"2002","unstructured":"GRAF H P , COSATTO E , STROM V , Visual prosody: Facial movements accompanying speech ; proceedings of the Proceedings of fifth IEEE international conference on automatic face gesture recognition, F, 2002 [C]. IEEE. GRAF H P, COSATTO E, STROM V, Visual prosody: Facial movements accompanying speech; proceedings of the Proceedings of fifth IEEE international conference on automatic face gesture recognition, F, 2002 [C]. IEEE."},{"key":"e_1_3_2_1_14_1","volume-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"MCAULIFFE M","year":"2017","unstructured":"MCAULIFFE M , SOCOLOF M , MIHUC S , Montreal forced aligner: Trainable text-speech alignment using kaldi ; proceedings of the Interspeech , F , 2017 [C]. MCAULIFFE M, SOCOLOF M, MIHUC S, Montreal forced aligner: Trainable text-speech alignment using kaldi; proceedings of the Interspeech, F, 2017 [C]."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"e_1_3_2_1_17_1","volume-title":"Espnet2-tts: Extending the edge of tts research [J]. arXiv preprint arXiv:211007840","author":"HAYASHI T","year":"2021","unstructured":"HAYASHI T , YAMAMOTO R , YOSHIMURA T , Espnet2-tts: Extending the edge of tts research [J]. arXiv preprint arXiv:211007840 , 2021 . HAYASHI T, YAMAMOTO R, YOSHIMURA T, Espnet2-tts: Extending the edge of tts research [J]. arXiv preprint arXiv:211007840, 2021."},{"key":"e_1_3_2_1_18_1","first-page":"17022","article-title":"Generative adversarial networks for efficient and high fidelity speech synthesis [J]","volume":"33","author":"KONG J","year":"2020","unstructured":"KONG J , KIM J , BAE J. Hifi-gan : Generative adversarial networks for efficient and high fidelity speech synthesis [J] . Advances in Neural Information Processing Systems , 2020 , 33 : 17022 - 17033 . KONG J, KIM J, BAE J. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis [J]. Advances in Neural Information Processing Systems, 2020, 33: 17022-33.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"AI2A '23: 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms","location":"Beijing China","acronym":"AI2A '23"},"container-title":["Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611450.3611476","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611450.3611476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:10Z","timestamp":1750178230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611450.3611476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":18,"alternative-id":["10.1145\/3611450.3611476","10.1145\/3611450"],"URL":"https:\/\/doi.org\/10.1145\/3611450.3611476","relation":{},"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"2023-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}