# Towards Multimodal Query-Based Spatial Audio Source Extraction

arXiv: https://arxiv.org/abs/2510.13308 · HTML: https://mlsanity.com/paper/2510.13308/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 15 Oct 2025.

## Built on by (most cited first, 1 of 1)

- [CoSTALA: Compositional Spatio-Temporal Audio-Language Alignment via Multi-Grain Hierarchical Contrastive Learning](https://mlsanity.com/paper/2608.24374/) (2026)

## Abstract (arXiv)

Query-based audio source extraction seeks to recover a target source from a mixture conditioned on a query. Existing approaches are largely confined to single-channel audio, leaving the spatial information in multi-channel recordings underexploited. We introduce a query-based spatial audio source extraction framework for recovering dry target signals from first-order ambisonics (FOA) mixtures. Our method accepts either an audio prompt or a text prompt as condition input, enabling flexible end-to-end extraction. The core of our proposed model lies in a tri-axial Transformer that jointly models temporal, frequency, and spatial channel dependencies. The model uses contrastive language-audio pretraining (CLAP) embeddings to enable unified audio-text conditioning via feature-wise linear modulation (FiLM). To eliminate costly annotations and improve generalization, we propose a label-free data pipeline that dynamically generates spatial mixtures and corresponding targets for training. The result of our experiment with high separation quality demonstrates the efficacy of multimodal conditioning and tri-axial modeling. This work establishes a new paradigm for high-fidelity spatial audio separation in immersive applications.