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 2008-05-30 13:40
Making a clear body-conducted speech with differential acceleration
Masashi Nakayama (TNCT/HCU), Shunsuke Ishimitsu (HCU), Seiji Nakagawa (AIST)
Abstract (in Japanese) (See Japanese page) 
(in English) Since body-conducted speech has a noise-robust characteristic under noise environment, noise-robust
speech recognition systems using body-conducted speech are expected. However, body-conducted signal can not
capture characteristics of high-frequency sounds sufficiently. In conventional methods to improve quality of body–
conducted speech, both speech and body-conducted speech are needed. On the other hand, we propose a method
using only a differential acceleration of body-conducted speech and conventional noise reduction methods. Results
of isolated word recognition experiments have shown significant effectiveness of the methods.
Keyword (in Japanese) (See Japanese page) 
(in English) Body-conducted speech / Speech / Body-conducted speech recognition / Speech recognition / Cross spectrum / Adaptive filter / /  
Reference Info. IEICE Tech. Rep., vol. 108, no. 69, EA2008-24, pp. 39-44, May 2008.
Paper # EA2008-24 
Date of Issue 2008-05-23 (EA, SIP) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee SIP EA  
Conference Date 2008-05-29 - 2008-05-30 
Place (in Japanese) (See Japanese page) 
Place (in English) Kansai Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To EA 
Conference Code 2008-05-SIP-EA 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Making a clear body-conducted speech with differential acceleration 
Sub Title (in English)  
Keyword(1) Body-conducted speech  
Keyword(2) Speech  
Keyword(3) Body-conducted speech recognition  
Keyword(4) Speech recognition  
Keyword(5) Cross spectrum  
Keyword(6) Adaptive filter  
Keyword(7)  
Keyword(8)  
1st Author's Name Masashi Nakayama  
1st Author's Affiliation Takamatsu National College of Technorogy/Hiroshima City University (TNCT/HCU)
2nd Author's Name Shunsuke Ishimitsu  
2nd Author's Affiliation Hiroshima City University (HCU)
3rd Author's Name Seiji Nakagawa  
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology (AIST)
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
Date Time 2008-05-30 13:40:00 
Presentation Time 25 
Registration for EA 
Paper # IEICE-EA2008-24,IEICE-SIP2008-33 
Volume (vol) IEICE-108 
Number (no) no.69(EA), no.71(SIP) 
Page pp.39-44 
#Pages IEICE-6 
Date of Issue IEICE-EA-2008-05-23,IEICE-SIP-2008-05-23 


[Return to Top Page]

[Return to IEICE Web Page]


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