The separation and localization of sound source signals are important techniques for many applications, such as highly realistic communication and speech recognition systems. These systems are expected to work without such prior information as the number of sound sources and the environmental conditions. In this paper, we developed a dodecahedral microphone array and proposed a novel separation method with our developed device. This method refers to human sound localization cues and uses acoustical characteristics obtained by the shape of the dodecahedral microphone array. Moreover, this method includes an estimation method of the number of sound sources that can operate without prior information. The sound source separation performances were evaluated under simulated and actual reverberant conditions, and the results were compared with the conventional method. The experimental results showed that our separation performance outperformed the conventional method.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Motoki OGASAWARA, Takanori NISHINO, Kazuya TAKEDA, "Blind Source Separation Using Dodecahedral Microphone Array under Reverberant Conditions" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 3, pp. 897-906, March 2011, doi: 10.1587/transfun.E94.A.897.
Abstract: The separation and localization of sound source signals are important techniques for many applications, such as highly realistic communication and speech recognition systems. These systems are expected to work without such prior information as the number of sound sources and the environmental conditions. In this paper, we developed a dodecahedral microphone array and proposed a novel separation method with our developed device. This method refers to human sound localization cues and uses acoustical characteristics obtained by the shape of the dodecahedral microphone array. Moreover, this method includes an estimation method of the number of sound sources that can operate without prior information. The sound source separation performances were evaluated under simulated and actual reverberant conditions, and the results were compared with the conventional method. The experimental results showed that our separation performance outperformed the conventional method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.897/_p
Copy
@ARTICLE{e94-a_3_897,
author={Motoki OGASAWARA, Takanori NISHINO, Kazuya TAKEDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blind Source Separation Using Dodecahedral Microphone Array under Reverberant Conditions},
year={2011},
volume={E94-A},
number={3},
pages={897-906},
abstract={The separation and localization of sound source signals are important techniques for many applications, such as highly realistic communication and speech recognition systems. These systems are expected to work without such prior information as the number of sound sources and the environmental conditions. In this paper, we developed a dodecahedral microphone array and proposed a novel separation method with our developed device. This method refers to human sound localization cues and uses acoustical characteristics obtained by the shape of the dodecahedral microphone array. Moreover, this method includes an estimation method of the number of sound sources that can operate without prior information. The sound source separation performances were evaluated under simulated and actual reverberant conditions, and the results were compared with the conventional method. The experimental results showed that our separation performance outperformed the conventional method.},
keywords={},
doi={10.1587/transfun.E94.A.897},
ISSN={1745-1337},
month={March},}
Copy
TY - JOUR
TI - Blind Source Separation Using Dodecahedral Microphone Array under Reverberant Conditions
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 897
EP - 906
AU - Motoki OGASAWARA
AU - Takanori NISHINO
AU - Kazuya TAKEDA
PY - 2011
DO - 10.1587/transfun.E94.A.897
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2011
AB - The separation and localization of sound source signals are important techniques for many applications, such as highly realistic communication and speech recognition systems. These systems are expected to work without such prior information as the number of sound sources and the environmental conditions. In this paper, we developed a dodecahedral microphone array and proposed a novel separation method with our developed device. This method refers to human sound localization cues and uses acoustical characteristics obtained by the shape of the dodecahedral microphone array. Moreover, this method includes an estimation method of the number of sound sources that can operate without prior information. The sound source separation performances were evaluated under simulated and actual reverberant conditions, and the results were compared with the conventional method. The experimental results showed that our separation performance outperformed the conventional method.
ER -