Eunwoo Song, Min-Jae Hwang, Ryuichi Yamamoto, Jin Seob Kim, Ohsung Kwon, Jae Min Kim. Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder. In Helen Meng, Bo Xu 0011, Thomas Fang Zheng, editors, Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020. pages 3570-3574, ISCA, 2020. [doi]
@inproceedings{SongHYKKK20,
title = {Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder},
author = {Eunwoo Song and Min-Jae Hwang and Ryuichi Yamamoto and Jin Seob Kim and Ohsung Kwon and Jae Min Kim},
year = {2020},
doi = {10.21437/Interspeech.2020-2116},
url = {https://doi.org/10.21437/Interspeech.2020-2116},
researchr = {https://researchr.org/publication/SongHYKKK20},
cites = {0},
citedby = {0},
pages = {3570-3574},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
editor = {Helen Meng and Bo Xu 0011 and Thomas Fang Zheng},
publisher = {ISCA},
}