Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays

TL;DR

This paper introduces a neural network approach that generalizes Ambisonics encoding to unseen microphone array geometries, enabling flexible and accurate spatial audio encoding without retraining for each array type.

Contribution

It presents a novel DNN-based method that incorporates array geometry into the encoding process, allowing generalization to arbitrary microphone array configurations unseen during training.

Findings

Improves Ambisonics encoding accuracy over conventional methods in dry conditions.

Shows frequency-dependent improvements in reverberant environments.

Validates effectiveness across multiple simulated acoustic scenarios.

Abstract

Using deep neural networks (DNNs) for encoding of microphone array (MA) signals to the Ambisonics spatial audio format can surpass certain limitations of established conventional methods, but existing DNN-based methods need to be trained separately for each MA. This paper proposes a DNN-based method for Ambisonics encoding that can generalize to arbitrary MA geometries unseen during training. The method takes as inputs the MA geometry and MA signals and uses a multi-level encoder consisting of separate paths for geometry and signal data, where geometry features inform the signal encoder at each level. The method is validated in simulated anechoic and reverberant conditions with one and two sources. The results indicate improvement over conventional encoding across the whole frequency range for dry scenes, while for reverberant scenes the improvement is frequency-dependent.