文献
J-GLOBAL ID:201802274756472159
整理番号:18A0852237
DNNベース音声合成における多重感情のモデリングと制御のための異なる表現の調査【JST・京大機械翻訳】
Investigating different representations for modeling and controlling multiple emotions in DNN-based speech synthesis
著者 (7件):
Lorenzo-Trueba Jaime
(National Institute of Informatics, 2-1-2 Hitotsubashi, Tokyo, Chiyoda-ku, Japan)
,
Eje Henter Gustav
(National Institute of Informatics, 2-1-2 Hitotsubashi, Tokyo, Chiyoda-ku, Japan)
,
Takaki Shinji
(National Institute of Informatics, 2-1-2 Hitotsubashi, Tokyo, Chiyoda-ku, Japan)
,
Yamagishi Junichi
(National Institute of Informatics, 2-1-2 Hitotsubashi, Tokyo, Chiyoda-ku, Japan)
,
Yamagishi Junichi
(The University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK)
,
Morino Yosuke
(Higashifuji Technical Center, Toyota Motor Corporation, Shizuoka Prefecture, 410-1193, Japan)
,
Ochiai Yuta
(Higashifuji Technical Center, Toyota Motor Corporation, Shizuoka Prefecture, 410-1193, Japan)
資料名:
Speech Communication
(Speech Communication)
巻:
99
ページ:
135-143
発行年:
2018年
JST資料番号:
W1590A
ISSN:
0167-6393
資料種別:
逐次刊行物 (A)
記事区分:
原著論文
発行国:
オランダ (NLD)
言語:
英語 (EN)