Acoustic source localization using time-difference of arrival and neural-network analysis

Nan Jiang; Jiancheng Dong; Ren Dong Ying

doi:10.1117/12.2008191

14 March 2013 Acoustic source localization using time-difference of arrival and neural-network analysis

Nan Jiang, Jiancheng Dong, Ren Dong Ying

Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 87686V (2013) https://doi.org/10.1117/12.2008191
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore

Abstract

The developing embedded technology requires revolutions in human-machine interaction. In this paper, we propose a novel method using localization of the taping sound on the table to replace the keyboard as manual input device. The method is applicable with a quad-channel-array collection of acoustic signals, from which the time-of-arrival differences and the position information could be estimated. In practice, as our table is in a limited size and the material properties are complex, the traditional localization algorithm based on time-of-arrival differences contains a sizable margin for error. Furthermore, we use neural-network analysis to improve recognition accuracy. Then experiments and simulations are carried out to verify this signal processing algorithm.

Citation Download Citation

Nan Jiang, Jiancheng Dong, and Ren Dong Ying "Acoustic source localization using time-difference of arrival and neural-network analysis", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87686V (14 March 2013); https://doi.org/10.1117/12.2008191

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available