Hearing in a shoe-box : binaural source position and wall absorption estimation using virtually supervised learning

TL;DR

This paper presents a virtually-supervised learning framework for binaural sound source localization and wall absorption estimation using simulated acoustic scenes, achieving accurate predictions of source positions and acoustic properties from binaural signals.

Contribution

It introduces a novel virtually-supervised learning approach with an acoustic room simulator to estimate source location and wall absorption from binaural audio.

Findings

Accurately estimates azimuth and elevation of sound sources.

Successfully predicts source range and wall absorption coefficients.

Incorporating diffusion effects enhances estimation accuracy.

Abstract

This paper introduces a new framework for supervised sound source localization referred to as virtually-supervised learning. An acoustic shoe-box room simulator is used to generate a large number of binaural single-source audio scenes. These scenes are used to build a dataset of spatial binaural features annotated with acoustic properties such as the 3D source position and the walls' absorption coefficients. A probabilistic high- to low-dimensional regression framework is used to learn a mapping from these features to the acoustic properties. Results indicate that this mapping successfully estimates the azimuth and elevation of new sources, but also their range and even the walls' absorption coefficients solely based on binaural signals. Results also reveal that incorporating random-diffusion effects in the data significantly improves the estimation of all parameters.