|
Probabilistic Structure
from Sound and Probabilistic Sound Source Localization
Chi-Hao Lin and Chieh-Chih Wang
2008 IEEE International Conference on
Advanced Robotics and its Social Impacts (ARSO)
Abstract |
Auditory
perception is one of the most important functions for robotics
applications. Microphone arrays are widely used for auditory perception
in which the spatial structure of microphones is usually known. The
structure from sound (SFS) approach addresses the problem of
simultaneously localizing a set of microphones and a set of acoustic
events which provides a great flexibility to calibrate different setups
of microphone arrays. However, the existing method does not take
measurement uncertainty into account and does not provide uncertainty
estimates of the SFS results. In this paper, we propose a probabilistic
structure from sound (PSFS) approach using the unscented transform. In
addition, a probabilistic sound source localization (PSSL) approach
using the PSFS results is provided to improve sound source localization
accuracy. The ample results of simulation and experiments using low
cost, off-the-shelf microphones demonstrate the feasibility and
performance of the proposed PSFS and PSSL approaches.
|
Download |
|
The full paper is available in PDF.
The demo video is available here.
|
Bibtex |
@inproceedings{Lin_arso08,
author = {Chi-Hao Lin and Chieh-Chih Wang},
title = {Probabilistic
Structure from Sound and Probabilistic Sound Source Localization},
booktitle = {IEEE
International Conference on Advanced Robotics and its Social Impacts
(ARSO)},
address = {Taipei, Taiwan},
month = {August},
year = {2008},
}
|
|
|
Copyright ©
Chieh-Chih
(Bob) Wang 2008. All right reserved.
Last Updated: August 8, 2008.
|
|