Improved feature extraction for CRNN-based multiple sound source localization
This work provides incremental improvements to sound source localization systems, which could benefit audio processing applications like hearing aids or robotics.
The authors tackled the problem of multiple sound source localization by improving feature extraction in a CRNN-based system using Ambisonics signals, achieving substantial performance improvements over the baseline network, particularly for localizing up to 3 sources.
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.