Sorry, you need to enable JavaScript to visit this website.

Learning Multiple Sound Source 2D Localization

Primary tabs

Citation Author(s):
Guillaume Le Moing, Phongtharin Vinayavekhin, Tadanobu Inoue, Jayakorn Vongkulbhisal, Asim Munawar, Ryuki Tachibana, Don Joven Agravante
Submitted by:
Phongtharin Vin...
Last updated:
29 September 2019 - 4:58am
Document Type:
Presentation Slides
Document Year:
Presenters Name:
Phongtharin Vinayavekhin
Paper Code:



In this paper, we propose novel deep learning based algorithms for multiple sound source localization. Specifically, we aim to find the 2D Cartesian coordinates of multiple sound sources in an enclosed environment by using multiple microphone arrays. To this end, we use an encoding-decoding architecture and propose two improvements on it to accomplish the task. In addition, we also propose two novel localization representations which increase the accuracy. Lastly, new metrics are developed relying on resolution-based multiple source association which enables us to evaluate and compare different localization approaches. We tested our method on both synthetic and real world data. The results show that our method improves upon the previous baseline approach for this problem.

0 users have voted:

Dataset Files