Logo image
Back
Sound source localization using complex-valued deep neural networks
Conference proceeding   Peer reviewed

Sound source localization using complex-valued deep neural networks

Gwantae Kim, David K. Han and Hanseok Ko
Proceedings of IEEE International Symposium on Consumer Electronics, pp 1-4
06 Jan 2024
DOI: https://doi.org/10.1109/ICCE59016.2024.10444246

Abstract

Artificial neural networks complex-valued deep neural network Computational modeling Direction-of-arrival estimation Feature extraction Location awareness sound source localization Time-frequency analysis Time Series Analysis
This paper presents a complex-valued deep neural network for sound source localization. Most neural network-based sound source localization approaches use time-frequency domain features. Even though both magnitude and phase play a pivotal role in solving the sound source localization problem, the real-valued features are only used because the neural network structures generally accept real-valued inputs only. In contrast, the complex-valued neural network structures directly receive complex-valued inputs and extract complex-valued hidden features. Therefore, the complex-valued deep neural network, which is proposed in this paper, has the potential to extract rich features for sound source localization. With a series of experiments, the proposed direction of arrival estimation method with a complex-valued deep neural network outperforms the real-valued deep neural network-based method.

Metrics

1 Record Views

Details

Logo image