PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs
Artem Dementyev, Wazeer Zulfikar, Sinan Hersek, Pascal Getreuer, Anurag Kumar, Vivek Kumar
Abstract
Current multimodal LLMs process audio as a mono stream, ignoring the rich spatial information essential for embodied AI. Existing spatial audio models, conversely, are constrained to fixed microphone geometries, preventing deployment across diverse devices. We present PhaseCoder, a transformer-only spatial audio encoder that is agnostic to microphone geometry. PhaseCoder takes raw multichannel audio and microphone coordinates as inputs to perform localization and produces robust spatial embeddings. We integrate PhaseCoder with the Gemma 3n LLM by finetuning it to reason over ``spatial audio tokens''. We show our encoder achieves state-of-the-art results on microphone-invariant localization benchmarks and, for the first time, enables an LLM to perform complex spatial reasoning and targeted transcription tasks from an arbitrary microphone array.
BibTeX
@inproceedings{
dementyev2026phasecoder,
title={PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal {LLM}s},
author={Artem Dementyev and Wazeer Zulfikar and Sinan Hersek and Pascal Getreuer and Anurag Kumar and Vivek Kumar},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=tU3raVqvYe}
}