ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2019-03-08 14:40
Affective Voice Generator by using Generative Adversarial Networks
Takuya Asakura, Shunsuke Akama, Shoji Yamamoto (TMCIT)
Abstract (in Japanese) (See Japanese page) 
(in English) A voice assistant device with internet connection has been spread in the world. An efficient use of this device is expected in the communication field such as monitoring and nursing care for elder people. In order to obtain social acceptance for the voice assistant device more than ever, it is necessary to equip the function of intercommunication with emotional behavior similar to human. Therefore, we developed the learning-based method to attach an affective voice to emotionless conversation by using Generative Adversarial Networks (GANs). In this method, we first extracted emotional specifications such as frequency and strength from database. Next, we applied GANs with controlling the attachment of emotional specifications in order to keep the basic property of emotionless conversation. Finally, the subjective evaluation for emotional expression and tone quality was performed by using the generated voice samples. As the result, it is conformed that our method is possible to generate some emotional expression on its conversation.
Keyword (in Japanese) (See Japanese page) 
(in English) Emotion / Voice / Machine Learning / Neural Networks / / / /  
Reference Info. ITE Tech. Rep., vol. 43, no. 8, HI2019-58, pp. 37-40, March 2019.
Paper # HI2019-58 
Date of Issue 2019-03-01 (HI, 3DIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee 3DMT HI  
Conference Date 2019-03-08 - 2019-03-08 
Place (in Japanese) (See Japanese page) 
Place (in English) Kogakuin Univ. Tokyo Urban Tech Tower Campus 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To HI 
Conference Code 2019-03-3DIT-HI 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Affective Voice Generator by using Generative Adversarial Networks 
Sub Title (in English)  
Keyword(1) Emotion  
Keyword(2) Voice  
Keyword(3) Machine Learning  
Keyword(4) Neural Networks  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Takuya Asakura  
1st Author's Affiliation Tokyo Metropolitan College of Industrial Technology (TMCIT)
2nd Author's Name Shunsuke Akama  
2nd Author's Affiliation Tokyo Metropolitan College of Industrial Technology (TMCIT)
3rd Author's Name Shoji Yamamoto  
3rd Author's Affiliation Tokyo Metropolitan College of Industrial Technology (TMCIT)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2019-03-08 14:40:00 
Presentation Time 20 minutes 
Registration for HI 
Paper # HI2019-58, 3DIT2019-10 
Volume (vol) vol.43 
Number (no) no.8 
Page pp.37-40 
#Pages
Date of Issue 2019-03-01 (HI, 3DIT) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan