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 2017-03-01 12:40
[Poster Presentation] An investigation of speaker adaptation method for DNN-based speech synthesis using speaker codes
Nobukatsu Hojo, Yusuke Ijima (NTT)
Abstract (in Japanese) (See Japanese page) 
(in English) In this work, we conducted objective evaluation experiments on the conventional speaker adaptation methods for DNN-based text-to-speech synthesis in order to compare their performance. One speaker adaptation method is based on speaker codes, which uses speaker codes as a input to the hidden layers. Besides the speaker adaptation method which reestimates the target speaker’s code, we have proposed the adaptation method to estimate the regression function for speaker codes. The other speaker adaptation method uses speaker dependent output layer, which shares hidden layers across all the speakers while the output layers are composed of speaker-dependent nodes. The model can be adapted to a target speaker by estimating regression layer parameters for the corresponding output layer. It has not been revealed how the difference of the model architecture and the number of adaptation parameters affects the performance. This work conducts speaker adaptation experiments using speech corpus which consists of 35 speakers’ speech data, and compared the performance by objective measure. From the experimental results, it was revealed that the speaker code-based models with more adaptation parameters show higher performance. It was also shown that the speaker code based models show comparable performance to speaker dependent output layer models when the number of adaptation parameters is set to large.
Keyword (in Japanese) (See Japanese page) 
(in English) speech synthesis / acoustic model / deep neural network / speaker codes / / / /  
Reference Info. IEICE Tech. Rep., vol. 116, no. 477, SP2016-103, pp. 147-152, March 2017.
Paper # SP2016-103 
Date of Issue 2017-02-22 (EA, SIP, SP) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee SP SIP EA  
Conference Date 2017-03-01 - 2017-03-02 
Place (in Japanese) (See Japanese page) 
Place (in English) Okinawa Industry Support Center 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics 
Paper Information
Registration To SP 
Conference Code 2017-03-SP-SIP-EA 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) An investigation of speaker adaptation method for DNN-based speech synthesis using speaker codes 
Sub Title (in English)  
Keyword(1) speech synthesis  
Keyword(2) acoustic model  
Keyword(3) deep neural network  
Keyword(4) speaker codes  
1st Author's Name Nobukatsu Hojo  
1st Author's Affiliation Nippon Telegraph and Telephone Corporation (NTT)
2nd Author's Name Yusuke Ijima  
2nd Author's Affiliation Nippon Telegraph and Telephone Corporation (NTT)
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 2017-03-01 12:40:00 
Presentation Time 90 
Registration for SP 
Paper # IEICE-EA2016-108,IEICE-SIP2016-163,IEICE-SP2016-103 
Volume (vol) IEICE-116 
Number (no) no.475(EA), no.476(SIP), no.477(SP) 
Page pp.147-152 
#Pages IEICE-6 
Date of Issue IEICE-EA-2017-02-22,IEICE-SIP-2017-02-22,IEICE-SP-2017-02-22 

[Return to Top Page]

[Return to IEICE Web Page]

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