{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:01:56Z","timestamp":1754161316749,"version":"3.41.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/iscit.2019.8905142","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T14:23:42Z","timestamp":1574691822000},"page":"64-69","source":"Crossref","is-referenced-by-count":4,"title":["Alternative Vietnamese Speech Synthesis System with Phoneme Structure"],"prefix":"10.1109","author":[{"given":"Quang Tuong","family":"Lam","sequence":"first","affiliation":[{"name":"OLLI Technology,HCMC University of Science,Ho Chi Minh city,Vietnam"}]},{"given":"Duc Hao","family":"Do","sequence":"additional","affiliation":[{"name":"OLLI Technology,HCMC University of Science,Ho Chi Minh city,Vietnam"}]},{"given":"Thanh Hung","family":"Vo","sequence":"additional","affiliation":[{"name":"HCMC University of Technology,Ho Chi Minh city,Vietnam"}]},{"given":"Duc Dung","family":"Nguyen","sequence":"additional","affiliation":[{"name":"HCMC University of Technology,Ho Chi Minh city,Vietnam"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Fast wavenet generation algorithm","author":"paine","year":"2016","journal-title":"CoRR"},{"key":"ref11","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref12","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"van den oord","year":"2013","journal-title":"Proceedings of the 35th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref13","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref14","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15625\/1813-9663\/34\/4\/13172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref17","article-title":"Hmm-based vietnamese text-to-speech: Prosodic phrasing modeling, system design, corpus design and evaluation","author":"nguyen","year":"2015","journal-title":"PhD thesis"},{"journal-title":"Vietnamese phonetics (in Vietnamese)","year":"1977","author":"doan","key":"ref18"},{"year":"2014","key":"ref19","article-title":"The Carnegie Mellon University Pronouncing Dictionary"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref6","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref8","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"CoRR"},{"key":"ref7","article-title":"Highway networks","author":"srivastava","year":"2015","journal-title":"CoRR"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"CoRR"},{"key":"ref1","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"CoRR"},{"journal-title":"Handbook of the International Phonetic Association A Guide to the Use of the International Phonetic Alphabet","year":"1999","author":"association","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2208629"},{"key":"ref21","article-title":"Sparse phase retrieval from short-time fourier measurements","author":"eldar","year":"2014","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"}],"event":{"name":"2019 19th International Symposium on Communications and Information Technologies (ISCIT)","start":{"date-parts":[[2019,9,25]]},"location":"Ho Chi Minh City, Vietnam","end":{"date-parts":[[2019,9,27]]}},"container-title":["2019 19th International Symposium on Communications and Information Technologies (ISCIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8896981\/8905110\/08905142.pdf?arnumber=8905142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:37:45Z","timestamp":1753731465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8905142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscit.2019.8905142","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}