Improved feature extraction for CRNN-based multiple sound source localization

TL;DR

This paper enhances a CRNN-based multi-source sound localization system by optimizing layer configurations to improve feature extraction, resulting in significantly better accuracy especially when localizing up to three sources.

Contribution

The paper introduces new convolutional layer configurations that reduce information loss, significantly boosting localization accuracy in multi-source scenarios.

Findings

Substantial accuracy improvement over baseline

Effective in localizing up to 3 sources

Validated on synthetic and real-world data

Abstract

In this work, we propose to extend a state-of-the-art multi-source localization system based on a convolutional recurrent neural network and Ambisonics signals. We significantly improve the performance of the baseline network by changing the layout between convolutional and pooling layers. We propose several configurations with more convolutional layers and smaller pooling sizes in-between, so that less information is lost across the layers, leading to a better feature extraction. In parallel, we test the system's ability to localize up to 3 sources, in which case the improved feature extraction provides the most significant boost in accuracy. We evaluate and compare these improved configurations on synthetic and real-world data. The obtained results show a quite substantial improvement of the multiple sound source localization performance over the baseline network.