Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio

TL;DR

This paper explores joint classification of sound source proximity and direction from binaural audio using deep neural networks, proposing methods to improve scene understanding in overlapping sound environments.

Contribution

It introduces novel approaches to split the sphere into directional classes and combines proximity and direction estimation into a unified DNN-based classification framework.

Findings

Effective joint estimation of proximity and direction achieved.

Proposed sphere-splitting methods improve directional classification.

Joint models provide temporal info on sound source onsets and offsets.

Abstract

Sound source proximity and distance estimation are of great interest in many practical applications, since they provide significant information for acoustic scene analysis. As both tasks share complementary qualities, ensuring efficient interaction between these two is crucial for a complete picture of an aural environment. In this paper, we aim to investigate several ways of performing joint proximity and direction estimation from binaural recordings, both defined as coarse classification problems based on Deep Neural Networks (DNNs). Considering the limitations of binaural audio, we propose two methods of splitting the sphere into angular areas in order to obtain a set of directional classes. For each method we study different model types to acquire information about the direction-of-arrival (DoA). Finally, we propose various ways of combining the proximity and direction estimation problems into a joint task providing temporal information about the onsets and offsets of the appearing sources. Experiments are performed for a synthetic reverberant binaural dataset consisting of up to two overlapping sound events.