Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities

H. Afifi, M. Guenther, A. Brendel, H. Karl, W. Kellermann, in: 14. ITG Conference on Speech Communication (ITG 2021), 2021.

Download
Restricted ITG_2021_paper_26 (3).pdf 283.62 KB
Conference Paper | English
Author
; ; ; ;
Abstract
Wireless Acoustic Sensor Networks (WASNs) have a wide range of audio signal processing applications. Due to the spatial diversity of the microphone and their relative position to the acoustic source, not all microphones are equally useful for subsequent audio signal processing tasks, nor do they all have the same wireless data transmission rates. Hence, a central task in WASNs is to balance a microphone’s estimated acoustic utility against its transmission delay, selecting a best-possible subset of microphones to record audio signals. In this work, we use reinforcement learning to decide if a microphone should be used or switched off to maximize the acoustic quality at low transmission delays, while minimizing switching frequency. In experiments with moving sources in a simulated acoustic environment, our method outperforms naive baseline comparisons
Publishing Year
Proceedings Title
14. ITG Conference on Speech Communication (ITG 2021)
LibreCat-ID

Cite this

Afifi H, Guenther M, Brendel A, Karl H, Kellermann W. Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. In: 14. ITG Conference on Speech Communication (ITG 2021). ; 2021.
Afifi, H., Guenther, M., Brendel, A., Karl, H., & Kellermann, W. (2021). Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. 14. ITG Conference on Speech Communication (ITG 2021).
@inproceedings{Afifi_Guenther_Brendel_Karl_Kellermann_2021, title={Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities}, booktitle={14. ITG Conference on Speech Communication (ITG 2021)}, author={Afifi, Haitham and Guenther, Michael and Brendel, Andreas and Karl, Holger and Kellermann, Walter}, year={2021} }
Afifi, Haitham, Michael Guenther, Andreas Brendel, Holger Karl, and Walter Kellermann. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” In 14. ITG Conference on Speech Communication (ITG 2021), 2021.
H. Afifi, M. Guenther, A. Brendel, H. Karl, and W. Kellermann, “Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities,” 2021.
Afifi, Haitham, et al. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” 14. ITG Conference on Speech Communication (ITG 2021), 2021.
All files available under the following license(s):
Creative Commons License:
CC-BYCreative Commons Attribution 4.0 International Public License (CC-BY 4.0)
Main File(s)
File Name
ITG_2021_paper_26 (3).pdf 283.62 KB
Access Level
Restricted Closed Access
Last Uploaded
2021-10-04T10:58:07Z


Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar