Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs

Abstract

In this paper, we present a new model for Direction of Arrival (DOA) estimation of sound sources based on an Icosahedral Convolutional Neural Network (CNN) applied over SRP-PHAT power maps computed from the signals received by a microphone array. This icosahedral CNN is equivariant to the 60 rotational symmetries of the icosahedron, which represent a good approximation of the continuous space of spherical rotations, and can be implemented using standard 2D convolutional layers, having a lower computational cost than most of the spherical CNNs. In addition, instead of using fully connected layers after the icosahedral convolutions, we propose a new soft-argmax function that can be seen as a differentiable version of the argmax function and allows us to solve the DOA estimation as a regression problem interpreting the output of the convolutional layers as a probability distribution. We prove that using models that fit the equivariances of the problem allows us to outperform other state-of-the-art models with a lower computational cost and more robustness, obtaining root mean square localization errors lower than 10° even in scenarios with a reverberation time $T_{60}$ of 1.5 s.

The code to reproduce this work can be found in our GitHub repository: https://github.com/DavidDiazGuerra/icoDOA

References in corpus (4)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• A Survey of Sound Source Localization with Deep Learning Methods
• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• BeamLearning: an end-to-end Deep Learning approach for the angular localization of sound sources using raw multichannel acoustic pressure data