{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:22:47Z","timestamp":1742646167059,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317420","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1030-1035","source":"Crossref","is-referenced-by-count":2,"title":["An Automatic Pipeline For Building Emotional Speech Dataset"],"prefix":"10.1109","author":[{"given":"Ngoc-Anh Nguyen","family":"Thi","sequence":"first","affiliation":[{"name":"Viettel Cyberspace Center, Viettel Group,Vietnam"}]},{"given":"Bao","family":"Thang Ta","sequence":"additional","affiliation":[{"name":"Viettel Cyberspace Center, Viettel Group,Vietnam"}]},{"given":"Nhat Minh","family":"Le","sequence":"additional","affiliation":[{"name":"Viettel Cyberspace Center, Viettel Group,Vietnam"}]},{"given":"Van","family":"Hai Do","sequence":"additional","affiliation":[{"name":"Viettel Cyberspace Center, Viettel Group,Vietnam"}]}],"member":"263","reference":[{"article-title":"A survey on neural speech synthesis","year":"2021","author":"Tan","key":"ref1"},{"article-title":"Review of end-to-end speech synthesis technology based on deep learning","year":"2021","author":"Mu","key":"ref2"},{"key":"ref3","article-title":"Multilingual techniques for low resource automatic speech recognition","volume-title":"Ph.D. dissertation","author":"Chuangsuwanich","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"volume-title":"Surrey audio-visual expressed emotion (savee) database","year":"2014","author":"Jackson","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-016-0406-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18201\/ijisae.2021473641"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2034"},{"article-title":"Interface databases: Design and collection of a multilingual emotional speech database","volume-title":"Proceedings of the Third International Conference on Language Resources and Evaluation (LREC\u201902)","author":"Hozjan","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2836"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3171965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-642"},{"key":"ref17","first-page":"114","article-title":"Modeling the prosody of Vietnamese attitudes for expressive speech synthesis","volume-title":"Proc. 3rd Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2012)","author":"Mac"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2023.026234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icce55644.2022.9852042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.25073\/2588-1086\/vnucsce.321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_17"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414542"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app12010327"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29516-5_5"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2022","author":"Ren","key":"ref29"},{"key":"ref30","first-page":"17 022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317420.pdf?arnumber=10317420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:53:30Z","timestamp":1710388410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317420","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}