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 2015-12-02 10:25
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine
Toru Nakashika (UEC), Tetsuya Takiguchi (Kobe Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we argue the way of modelling speech signals using improved three-way restricted Boltzmann machine (3WRBM) where acoustic features, latent phonological features, and speaker-identity features are considered. The 3WRBM is an energy-based probabilistic model that includes three kinds of potentials: unary potentials of each variable, pairwise potentials of every two variables, and three-way potentials of the three variables. In our approach, we design the three-way potentials properly in the speaker-adaptive training (SAT) manner. The optimized model captures the relationships between the variables, enables to compute conditional probabilities of each variables, and is appliable to many tasks in speech signal processing. For example, estimating speaker-identity features given acoustic features is used for speaker recognition. Another example is estimating acoustic features from the phonological features that are estimated given source speaker's acoustic features and the desired speaker-identity features; that is voice conversion. In our experiments, we evaluate the effectiveness of the speech modelling through a voice conversion task and a speaker recognition task.
Keyword (in Japanese) (See Japanese page) 
(in English) speech modelling / restricted Boltzmann machine / speaker-adaptive training / speaker recognition / voice conversion / / /  
Reference Info. IEICE Tech. Rep., vol. 115, no. 346, SP2015-71, pp. 7-12, Dec. 2015.
Paper # SP2015-71 
Date of Issue 2015-11-25 (SP) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380
Notes on Review This article is a technical report without peer review, and its polished version will be published elsewhere.

Conference Information
Conference Date 2015-12-02 - 2015-12-04 
Place (in Japanese) (See Japanese page) 
Place (in English) Nagoya Inst of Tech. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) The Second Natural Language Processing Symposium & The 17th Spoken Language Symposium 
Paper Information
Registration To SP 
Conference Code 2015-12-NLC-NL-SP-SLP 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine 
Sub Title (in English)  
Keyword(1) speech modelling  
Keyword(2) restricted Boltzmann machine  
Keyword(3) speaker-adaptive training  
Keyword(4) speaker recognition  
Keyword(5) voice conversion  
1st Author's Name Toru Nakashika  
1st Author's Affiliation The University of Electro-Communications (UEC)
2nd Author's Name Tetsuya Takiguchi  
2nd Author's Affiliation Kobe University (Kobe Univ.)
3rd Author's Name  
3rd Author's Affiliation ()
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 ()
Date Time 2015-12-02 10:25:00 
Presentation Time 25 
Registration for SP 
Paper # IEICE-SP2015-71 
Volume (vol) IEICE-115 
Number (no) no.346 
Page pp.7-12 
#Pages IEICE-6 
Date of Issue IEICE-SP-2015-11-25 

[Return to Top Page]

[Return to IEICE Web Page]

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