DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models
Year: 2026
Type: conference-paper
Abstract: Reasoning about spatial audio with large language models requires a spatial audio encoder as an acoustic front-end to obtain audio embeddings for further processing. Such an encoder needs to capture all information required to detect the type of sound events, as well as the direction and distance of their corresponding sources. Accomplishing this with a single audio encoder is demanding as the information required for each of these tasks is mostly independent of each other. As a result, the performance obtained with a single encoder is often worse than when using task-specific audio encoders. In this work, we present DSpAST, a novel audio encoder based on SpatialAST that learns disentangled representations of spatial audio while having only 0.2% additional parameters. Experiments on SpatialSoundQA with the spatial audio reasoning system BAT demonstrate that DSpAST significantly outperforms SpatialAST.
Authors: Kevin Wilkinghoff, Zheng-Hua Tan
Institution: Aalborg University
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416255468
FWCI:
Cites:
Cited by:
Related to: