# Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics

arXiv: https://arxiv.org/abs/2609.23152 · HTML: https://mlsanity.com/paper/2609.23152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [Scaling up masked audio encoder learning for general audio classification](https://mlsanity.com/paper/2406.06992/) (2024)
- [STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events](https://mlsanity.com/paper/2306.09126/) (2023)
- [BAT: Learning to Reason about Spatial Sounds with Large Language Models](https://mlsanity.com/paper/2402.01591/) (2024)
- [Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks](https://mlsanity.com/paper/2306.04186/) (2023)
- [A Dataset of Dynamic Reverberant Sound Scenes with Directional Interferers for Sound Event Localization and Detection](https://mlsanity.com/paper/2106.06999/) (2021)
- [Learning Spatially-Aware Language and Audio Embeddings](https://mlsanity.com/paper/2409.11369/) (2024)
- [SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations](https://mlsanity.com/paper/2510.25955/) (2025)
- [Sci-Phi: A Large Language Model Spatial Audio Descriptor](https://mlsanity.com/paper/2510.05542/) (2025)
- [w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training](https://mlsanity.com/paper/2312.06907/) (2023)

## Abstract (arXiv)

Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spatial representation of sound scenes, we introduce Bearings. Bearings is a self-supervised framework that learns soundfield embeddings from unlabeled first-order Ambisonics. We pre-train a masked auto-encoder paired with a decoder conditioned on frozen acoustic embeddings from an off-the-shelf single-channel audio encoder. Our results show that the resulting soundfield embeddings form a reusable stream that can be attached to frozen acoustic encoders with a lightweight trainable fusion head. On sound event localization and detection, concatenating our soundfield embeddings with acoustic representations provides the missing spatial information and enables joint detection and localization, raising the location-dependent F-score from below 4 to 50 on TAU-NIGENS 2021 and 39 on STARSS23. To our knowledge, Bearings is the first self-supervised soundfield encoder whose embeddings plug into frozen acoustic encoders without retraining either model.