Controlling the Strength of Emotions in Speech-like Emotional Sound Generated by WaveNet
Authors: Kento Matsumoto, Sunao Hara, Masanobu Abe
In this page, there are generated speeches by our proposed method[1].
Generated Neutral
Generated Angry
Generated Happy
Spe-Vus-1
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Spe-Vus-2
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Vus-1
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Vus-2
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
No
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Conv
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
Your browser does not support the HTML5
[1]Kento Matsumoto, Sunao Hara, and Masanobu Abe, “Controlling the Strength of Emotions in Speech-like Emotional Sound Generated by WaveNet,” Interspeech 2020, pp. 3421-3425 (5 pages), Virtual Conference (Shanghai, China), Oct. 2020
Contact
k_matsu
＠
s.okayama-u.ac.jp
(＠->@)