# AxLSTMs: learning self-supervised audio representations with xLSTMs

arXiv: https://arxiv.org/abs/2408.16568 · HTML: https://mlsanity.com/paper/2408.16568/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2024.

## Built on by (most cited first, 3 of 3)

- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement](https://mlsanity.com/paper/2507.00966/) (2025)
- [An overview of neural architectures for self-supervised audio representation learning from masked spectrograms](https://mlsanity.com/paper/2509.18691/) (2025)

## Abstract (arXiv)

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have observed a lot of renewed interest, including the extended long short-term memory (xLSTM) architecture, which reinvigorates the original LSTM. However, while xLSTMs have shown competitive performance compared to the transformer, their viability for learning self-supervised general-purpose audio representations has not been evaluated. This work proposes Audio xLSTM (AxLSTM), an approach for learning audio representations from masked spectrogram patches in a self-supervised setting. Pretrained on the AudioSet dataset, the proposed AxLSTM models outperform comparable self-supervised audio spectrogram transformer (SSAST) baselines by up to 25% in relative performance across a set of ten diverse downstream tasks while having up to 45% fewer parameters.