Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays
This addresses a practical limitation in spatial audio processing for applications like VR/AR, though it appears incremental as it builds on existing DNN approaches.
The paper tackles the problem of DNN-based Ambisonics encoding requiring separate training for each microphone array geometry by proposing a method that generalizes to unseen geometries, showing improvement over conventional encoding across frequencies for dry scenes and frequency-dependent improvement for reverberant scenes.
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.