arXiv · 2611.13687
AURA: Auditory Spatial Intelligence via a Unified Representation from a General-Audio Encoder through Complete Alignment
Abstract
Answering spatial questions about multi-source scenes requires a model both to identify each sound and to locate it. Existing spatial audio-language models obtain spatial information from a dedicated encoder, which separates spatial and semantic processing into distinct feature spaces. We study whether a general-audio codec trained without spatial supervision can serve both purposes. A controlled layer-wise analysis shows that the frozen codec retains spatial information, with lateral cues carried by the difference between the two ear channels. This information, however, is not readily accessible: in dual-source scenes, a model trained on these features predicts left/right at chance and, on the remaining axes, assigns the detected direction to the queried and the non-queried source equally often. We attribute this failure to an audio--text information asymmetry, in which the audio contains both sources while the answer describes only the queried one. A controlled $2\times2$ experiment shows that either completing the scene description or exposing the inter-channel difference lifts left/right accuracy above chance, whereas binding directions to the queried source requires both. Building on these findings, AURA keeps the codec and the language model frozen and exceeds the strongest dedicated system on SpatialSoundQA by 10.31 points in dual-source direction accuracy, with about 40\% of its trainable parameters.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Boyan Han, Xiaoyan Wang, Zhe Sun, Ziqi Wang, Yujun Cai, Hongli Cao, Yiwei Wang, Ming-Hsuan Yang, Liang An. 2026-11-10. AURA: Auditory Spatial Intelligence via a Unified Representation from a General-Audio Encoder through Complete Alignment. https://searcharxiv.com/abs/2611.13687
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.