Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio
This work addresses acoustic scene analysis for applications like audio processing, but it is incremental as it builds on existing DNN methods for binaural audio.
The paper tackled joint proximity and direction estimation from binaural audio by proposing methods for splitting the sphere into angular areas and combining tasks into a joint classification problem using DNNs, achieving results on a synthetic dataset with up to two overlapping sound events.
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.