Distance-Based Sound Separation

TL;DR

This paper introduces distance-based sound separation, a new task where sounds are separated based solely on their proximity to a microphone, aiding focus in noisy environments.

Contribution

It presents a neural network approach for separating near and far sounds using distance as the criterion, demonstrating feasibility in synthetic reverberant conditions.

Findings

Achieved 4.4 dB SI-SNR improvement for near sounds

Achieved 6.8 dB SI-SNR improvement for far sounds

Validated the approach with a single microphone and multiple speakers

Abstract

We propose the novel task of distance-based sound separation, where sounds are separated based only on their distance from a single microphone. In the context of assisted listening devices, proximity provides a simple criterion for sound selection in noisy environments that would allow the user to focus on sounds relevant to a local conversation. We demonstrate the feasibility of this approach by training a neural network to separate near sounds from far sounds in single channel synthetic reverberant mixtures, relative to a threshold distance defining the boundary between near and far. With a single nearby speaker and four distant speakers, the model improves scale-invariant signal to noise ratio by 4.4 dB for near sounds and 6.8 dB for far sounds.