cs.SDOct 31, 2026

Spatial DJ: Spatial Audio Control for Arbitrary Loudspeaker Layouts

Authors: Anastasia Geleta, Margarita Geleta

Organizations: AVINCE, San Francisco, CA 94115, USA · Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA 94720, USA

Abstract

Object-based spatial audio promises render-anywhere playback, yet deploying it in a new venue still requires two tasks that are rarely addressed together: acquiring the physical loudspeaker geometry and enabling creators manipulate spatial audio while listening through the target loudspeaker system rather than a headphone proxy. We present Spatial DJ, a system for on-site loudspeaker layout acquisition and real-time spatial audio rendering and control, using head-worn AR in a coordinate frame aligned to the physical loudspeakers. In an 18-loudspeaker room, we evaluate calibration accuracy, repeatability, and control latency, and conduct an 18-participant listener study comparing diffuse and orbiting point-source rendering configurations applied to vocal and instrumental layers. Orbiting point-source conditions received higher ratings of perceived immersion, energy, and novelty than the diffuse baseline. Beyond this controlled setting, four representative deployments illustrate reuse of the same system across heterogeneous loudspeaker venues.

Figures & tables

Explore similar work

Jun 4, 2026

Probing Spatial Structure in Pretrained Audio Representations

Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are consistently easier to decode than room factors; and sensitivity analysis under controlled perturbations shows heterogeneous responses to source and room variation. These results reveal systematic biases in current pretrained audio representations. SARL is released as an open-source benchmark for reproducible evaluation of spatial audio representations.
Nov 2, 2026

Ananas: A Networked Audio System for Distributed Spatial Audio Applications

Spatial audio has an accessibility problem. Largescale spatial and immersive audio installations remain costly and exclusive, with high barriers to entry. We propose ''Ananas,'' a networked audio system consisting of network protocols, control software and microcontroller firmware, with the aim of rendering spatial audio applications accessible to a broad cohort of potential users. Based on a network of low-cost microcontroller development boards programmed in the Faust programming language, synchronised to nanosecond order via IEEE 1588 Precision Time Protocol, and controlled by approachable, digital audio workstation-based tooling, Ananas represents an opportunity to disrupt and democratise the spatial audio landscape. In this paper we demonstrate Ananas's protocols for audio and control data transmission and device discovery, its methods for media clock and presentation time recovery, and its applications to wave field synthesis and higher order ambisonics in a modular, scalable form.
Oct 12, 2026

SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning

Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried time or interval, a challenge intensified by overlapping speech and source motion. To study this problem, we introduce Sonic-Bench, comprising 2.8K first-order Ambisonics clips and 28.8K target-specific question-answer pairs across 480 simulated indoor scenes. The benchmark covers localization, distance estimation, and motion reasoning in single- and dual-source settings. We further propose SonicWorld, which integrates physical, learned acoustic, and semantic features into persistent source states through learned transitions and recurrent updates, and projects them into an Omni LLM for spatial reasoning. Compared with Spatial-Omni on the Sonic-Bench test split, SonicWorld improves direction accuracy from 31.98% to 34.69% and reduces azimuth error from 57.22° to 48.01°. In zero-shot transfer to Spatial LibriSpeech, SonicWorld retains strong localization performance, achieving 73.98% direction accuracy and 19.29° azimuth error, compared with 27.14% and 70.74° for Spatial-Omni.