文献
J-GLOBAL ID:202002268912484192
整理番号:20A0779273
自己注意に基づくエンドツーエンド音声合成のための局所性モデリングについて
On the localness modeling for the self-attention based end-to-end speech synthesis
著者 (8件):
Yang Shan
(Audio, Speech and Language Processing Group (ASLP@NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China)
,
Lu Heng
(Tencent AI Lab, China)
,
Kang Shiyin
(Tencent AI Lab, China)
,
Xue Liumeng
(Audio, Speech and Language Processing Group (ASLP@NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China)
,
Xiao Jinba
(Audio, Speech and Language Processing Group (ASLP@NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China)
,
Su Dan
(Tencent AI Lab, China)
,
Xie Lei
(Audio, Speech and Language Processing Group (ASLP@NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China)
,
Yu Dong
(Tencent AI Lab, China)
資料名:
Neural Networks
(Neural Networks)
巻:
125
ページ:
121-130
発行年:
2020年05月
JST資料番号:
T0698A
ISSN:
0893-6080
資料種別:
逐次刊行物 (A)
記事区分:
原著論文
発行国:
イギリス (GBR)
言語:
英語 (EN)