# SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays

arXiv: https://arxiv.org/abs/2610.05610 · HTML: https://mlsanity.com/paper/2610.05610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [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)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [Joint Audio and Speech Understanding](https://mlsanity.com/paper/2309.14405/) (2023)
- [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)
- [Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019](https://mlsanity.com/paper/2009.02792/) (2020)
- [Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training](https://mlsanity.com/paper/2110.07124/) (2021)
- [Learning Spatially-Aware Language and Audio Embeddings](https://mlsanity.com/paper/2409.11369/) (2024)
- [OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models](https://mlsanity.com/paper/2509.26140/) (2025)
- [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)
- [The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models](https://mlsanity.com/paper/2601.02954/) (2026)
- [PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs](https://mlsanity.com/paper/2601.21124/) (2026)
- [DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models](https://mlsanity.com/paper/2509.13927/) (2025)
- [Sci-Phi: A Large Language Model Spatial Audio Descriptor](https://mlsanity.com/paper/2510.05542/) (2025)
- [Ambisonics Encoding For Arbitrary Microphone Arrays Incorporating Residual Channels For Binaural Reproduction](https://mlsanity.com/paper/2402.17362/) (2024)
- [M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses](https://mlsanity.com/paper/2409.11494/) (2024)
- [Design and Analysis of Binaural Signal Matching with Arbitrary Microphone Arrays and Listener Head Rotations](https://mlsanity.com/paper/2408.03581/) (2024)

## Abstract (arXiv)

Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio within complex environments. While large audio-language models excel at mono-channel reasoning, they lack spatial awareness, discarding critical spatial cues that enable sound localization and that can improve the disentanglement of overlapping sound sources. To address this, we present SEA-LM, a Spatial Audio Understanding model. First, we introduce FOACODER, a layout-flexible spatial audio encoder trained on source localization and ego-centric voice activity detection objectives to encode First Order Ambisonics derived from variable-count, variable-position smart-glasses arrays via beamforming. We train a Multimodal Large Language Model (MLLM) to understand these spatial audio embeddings through a two-stage curriculum spanning six tasks, including sound localization and spatially selective transcription in settings with multiple speakers and overlapping sounds. To prevent the transcription outputs from dominating the next token prediction loss and overwhelming the direction predictions, we introduce a Spatio-temporal Weighted Cross-Entropy Loss. On our evaluation set, SEA-LM achieves lower azimuth and elevation MAE, higher temporal IoU, lower external-source hallucination and missing-source rates, and lower WER on most transcription tasks than compared baselines, while remaining robust across 1,211 smart-glasses array configurations with 4 to 9 microphones.