# Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events

## TL;DR

This paper introduces a quaternion convolutional neural network that effectively detects and localizes 3D sound events by leveraging the internal dependencies of spherical harmonic components in ambisonic signals, enhancing accuracy.

## Contribution

The paper presents a novel quaternion CNN approach for processing spherical harmonic components of 3D sound signals, improving detection and localization performance over traditional methods.

## Key findings

- Improved accuracy in 3D sound event detection.
- Effective exploitation of ambisonic signal correlations.
- Enhanced localization precision.

## Abstract

Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity. One of the models that perfectly suits with quaternion-valued data processing is represented by 3D acoustic signals in their spherical harmonics decomposition. In this paper, we address the problem of localizing and detecting sound events in the spatial sound field by using quaternion-valued data processing. In particular, we consider the spherical harmonic components of the signals captured by a first-order ambisonic microphone and process them by using a quaternion convolutional neural network. Experimental results show that the proposed approach exploits the correlated nature of the ambisonic signals, thus improving accuracy results in 3D sound event detection and localization.