IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
... (for ESS/CS/ES/ISS)
Tech. Rep. Archives
... (for ES/CS)
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2018-12-07 15:55

Toyoaki Kuwahara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC)
Abstract (in Japanese) (See Japanese page) 
(in English) The emotion estimation by speech makes it possible to estimate with higher precision with the development of deep learning. However, most of the emotion estimation using deep learning is using supervised learning, and there is a problem that it is difficult to secure a large amount of data set used for learning.
In addition, when the training data environment and the actual data environment are significantly different, it is considered as a problem that the accuracy of emotion estimation greatly deteriorates.
Therefore, as an approach to solve both problems, in this research, smoothing of the generated emotion estimation model is performed using virtual adversal training (VAT), semi-teacher learning, and the robustness of the model Improvement was aimed. VAT attracts attention in machine learning as a method of smoothing a generation model by adding minute and intentional perturbation to training data in learning. We first showed improvement of robustness of model generated by setting hyperparameter in VAT by verification with single corpus and then performing evaluation experiment with cross corpus.
Keyword (in Japanese) (See Japanese page) 
(in English) Deep Learning / Cross Corpus / Virtual Adversarial Training / Emotion Recognition / Speech Processing / / /  
Reference Info. IEICE Tech. Rep., vol. 118, no. 350, AI2018-30, pp. 25-29, Dec. 2018.
Paper # AI2018-30 
Date of Issue 2018-11-30 (AI) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee AI  
Conference Date 2018-12-07 - 2018-12-08 
Place (in Japanese) (See Japanese page) 
Place (in English)  
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To AI 
Conference Code 2018-12-AI 
Language Japanese without English title) 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English)  
Sub Title (in English)  
Keyword(1) Deep Learning  
Keyword(2) Cross Corpus  
Keyword(3) Virtual Adversarial Training  
Keyword(4) Emotion Recognition  
Keyword(5) Speech Processing  
1st Author's Name Toyoaki Kuwahara  
1st Author's Affiliation The University of Electro-Communications (UEC)
2nd Author's Name Yuichi Sei  
2nd Author's Affiliation The University of Electro-Communications (UEC)
3rd Author's Name Yasuyuki Tahara  
3rd Author's Affiliation The University of Electro-Communications (UEC)
4th Author's Name Akihiko Ohsuga  
4th Author's Affiliation The University of Electro-Communications (UEC)
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 ()
Date Time 2018-12-07 15:55:00 
Presentation Time 25 
Registration for AI 
Paper # IEICE-AI2018-30 
Volume (vol) IEICE-118 
Number (no) no.350 
Page pp.25-29 
#Pages IEICE-5 
Date of Issue IEICE-AI-2018-11-30 

[Return to Top Page]

[Return to IEICE Web Page]

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan