# DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models

arXiv: https://arxiv.org/abs/2509.13927 · HTML: https://mlsanity.com/paper/2509.13927/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 30 of 30)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning](https://mlsanity.com/paper/2206.08312/) (2022)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers](https://mlsanity.com/paper/2307.03183/) (2023)
- [Vision Transformer with Quadrangle Attention](https://mlsanity.com/paper/2303.15105/) (2023)
- [BAT: Learning to Reason about Spatial Sounds with Large Language Models](https://mlsanity.com/paper/2402.01591/) (2024)
- [Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy](https://mlsanity.com/paper/1905.00268/) (2019)
- [Can Large Language Models Understand Spatial Audio?](https://mlsanity.com/paper/2406.07914/) (2024)
- [SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing](https://mlsanity.com/paper/2506.05414/) (2025)
- [Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms](https://mlsanity.com/paper/2401.12238/) (2024)
- [Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities](https://mlsanity.com/paper/2312.00249/) (2023)
- [Extending GCC-PHAT using Shift Equivariant Neural Networks](https://mlsanity.com/paper/2208.04654/) (2022)
- [Two vs. Four-Channel Sound Event Localization and Detection](https://mlsanity.com/paper/2309.13343/) (2023)
- [Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations](https://mlsanity.com/paper/2508.08399/) (2025)
- [Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder](https://mlsanity.com/paper/2211.08191/) (2022)
- [Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder](https://mlsanity.com/paper/2409.03520/) (2024)
- [Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays](https://mlsanity.com/paper/2501.08047/) (2025)
- [Baseline Systems and Evaluation Metrics for Spatial Semantic Segmentation of Sound Scenes](https://mlsanity.com/paper/2503.22088/) (2025)
- [Description and Discussion on DCASE 2025 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes](https://mlsanity.com/paper/2506.10676/) (2025)
- [Learning Robust Spatial Representations from Binaural Audio through Feature Distillation](https://mlsanity.com/paper/2508.20914/) (2025)
- [Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification](https://mlsanity.com/paper/2209.05900/) (2022)
- [Past, Present, and Future of Spatial Audio and Room Acoustics](https://mlsanity.com/paper/2503.12948/) (2025)
- [Factorized RVQ-GAN For Disentangled Speech Tokenization](https://mlsanity.com/paper/2506.15456/) (2025)

## Built on by (most cited first, 5 of 5)

- [SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models](https://mlsanity.com/paper/2511.06606/) (2025)
- [OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents](https://mlsanity.com/paper/2609.23407/) (2026)
- [Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models](https://mlsanity.com/paper/2606.14820/) (2026)
- [SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former](https://mlsanity.com/paper/2609.34347/) (2026)
- [SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays](https://mlsanity.com/paper/2610.05610/) (2026)

## Abstract (arXiv)

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.