SANN-PSZ: Spatially Adaptive Neural Network for Head-Tracked Personal Sound Zones

TL;DR

This paper introduces SANN-PSZ, a deep learning-based system that dynamically creates personal sound zones with head tracking, offering improved robustness, efficiency, and real-time adaptability over traditional methods.

Contribution

The paper presents a novel spatially adaptive neural network for real-time personal sound zone rendering that outperforms traditional filter design methods in robustness and efficiency.

Findings

Augmenting room reflections improves model robustness.

Adding filter compactness constraints does not harm performance.

The model achieves 100x data compression and 10x computational efficiency.

Abstract

A deep learning framework for dynamically rendering personal sound zones (PSZs) with head tracking is presented, utilizing a spatially adaptive neural network (SANN) that inputs listeners' head coordinates and outputs PSZ filter coefficients. The SANN model is trained using either simulated acoustic transfer functions (ATFs) with data augmentation for robustness in uncertain environments or a mix of simulated and measured ATFs for customization under known conditions. It is found that augmenting room reflections in the training data can more effectively improve the model robustness than augmenting the system imperfections, and that adding constraints such as filter compactness to the loss function does not significantly affect the model's performance. Comparisons of the best-performing model with traditional filter design methods show that, when no measured ATFs are available, the model yields equal or higher isolation in an actual room environment with fewer filter artifacts. Furthermore, the model achieves significant data compression (100x) and computational efficiency (10x) compared to the traditional methods, making it suitable for real-time rendering of PSZs that adapt to the listeners' head movements.