Binaural Localization Model for Speech in Noise

TL;DR

This paper introduces a lightweight end-to-end binaural localization model for speech in noisy environments, incorporating ear noise modeling and outperforming traditional algorithms in localization accuracy.

Contribution

The paper presents a novel convolutional recurrent network for binaural speech localization that accounts for ear noise and is validated against human performance.

Findings

Model outperforms steered response power algorithm in localization accuracy.

Incorporating ear noise improves model realism and robustness.

Listening tests show comparable performance to humans in noisy conditions.

Abstract

Binaural acoustic source localization is important to human listeners for spatial awareness, communication and safety. In this paper, an end-to-end binaural localization model for speech in noise is presented. A lightweight convolutional recurrent network that localizes sound in the frontal azimuthal plane for noisy reverberant binaural signals is introduced. The model incorporates additive internal ear noise to represent the frequency-dependent hearing threshold of a typical listener. The localization performance of the model is compared with the steered response power algorithm, and the use of the model as a measure of interaural cue preservation for binaural speech enhancement methods is studied. A listening test was performed to compare the performance of the model with human localization of speech in noisy conditions.