文献
J-GLOBAL ID:202002261523928973
整理番号:20A1614274
畳込みニューラルネットワークに基づく高速で高品質歌声合成システム【JST・京大機械翻訳】
Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks
著者 (6件):
Nakamura Kazuhiro
(Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
,
Takaki Shinji
(Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
,
Hashimoto Kei
(Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
,
Oura Keiichiro
(Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
,
Nankaku Yoshihiko
(Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan)
,
Tokuda Keiichi
(Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
資料名:
IEEE Conference Proceedings
(IEEE Conference Proceedings)
巻:
2020
号:
ICASSP
ページ:
7239-7243
発行年:
2020年
JST資料番号:
W2441A
資料種別:
会議録 (C)
記事区分:
原著論文
発行国:
アメリカ合衆国 (USA)
言語:
英語 (EN)