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 2013-12-19 17:15
Speaker-dependent conditional restricted Boltzmann machine for voice conversion
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we present a voice conversion (VC) method that utilizes conditional restricted Boltzmann machines (CRBMs) for each speaker to obtain time-invariant speaker-independent spaces where voice features are converted more easily than those in an original acoustic feature space. First, we train two CRBMs for a source and target speaker independently using speaker-dependent training data (without the need to parallelize the training data). Then, a small number of parallel data are fed into each CRBM and the high-order features produced by the CRBMs are used to train a concatenating neural network (NN) between the two CRBMs. Finally, the entire network (the two CRBMs and the NN) is fine-tuned using the acoustic parallel data. Through voice-conversion experiments, we confirmed the high performance of our method in terms of objective and subjective evaluations, comparing it with conventional GMM, NN, and speaker-dependent DBN approaches.
Keyword (in Japanese) (See Japanese page) 
(in English) Voice conversion / conditional restricted Boltzmann machine / deep learning / speaker specific features / / / /  
Reference Info. IEICE Tech. Rep., vol. 113, no. 366, SP2013-88, pp. 83-88, Dec. 2013.
Paper # SP2013-88 
Date of Issue 2013-12-12 (SP) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee SP IPSJ-SLP  
Conference Date 2013-12-19 - 2013-12-20 
Place (in Japanese) (See Japanese page) 
Place (in English)  
Topics (in Japanese) (See Japanese page) 
Topics (in English) 15th Symposium on Spoken Language 
Paper Information
Registration To SP 
Conference Code 2013-12-SP-SLP 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Speaker-dependent conditional restricted Boltzmann machine for voice conversion 
Sub Title (in English)  
Keyword(1) Voice conversion  
Keyword(2) conditional restricted Boltzmann machine  
Keyword(3) deep learning  
Keyword(4) speaker specific features  
1st Author's Name Toru Nakashika  
1st Author's Affiliation Kobe University (Kobe Univ.)
2nd Author's Name Tetsuya Takiguchi  
2nd Author's Affiliation Kobe University (Kobe Univ.)
3rd Author's Name Yasuo Ariki  
3rd Author's Affiliation Kobe University (Kobe Univ.)
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 2013-12-19 17:15:00 
Presentation Time 25 
Registration for SP 
Paper # IEICE-SP2013-88 
Volume (vol) IEICE-113 
Number (no) no.366 
Page pp.83-88 
#Pages IEICE-6 
Date of Issue IEICE-SP-2013-12-12 

[Return to Top Page]

[Return to IEICE Web Page]

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