# SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation

arXiv: https://arxiv.org/abs/2408.05057 · HTML: https://mlsanity.com/paper/2408.05057/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 9 Aug 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Speech and audio SSMs](https://mlsanity.com/ssm/speech-and-audio-ssms/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation](https://mlsanity.com/paper/2403.18257/) (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)
- [An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection](https://mlsanity.com/paper/2010.13092/) (2020)
- [ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes](https://mlsanity.com/paper/2403.05795/) (2024)
- [Sound Event Detection and Localization with Distance Estimation](https://mlsanity.com/paper/2403.11827/) (2024)
- [CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection](https://mlsanity.com/paper/2312.12821/) (2023)
- [A Track-Wise Ensemble Event Independent Network for Polyphonic Sound Event Localization and Detection](https://mlsanity.com/paper/2203.10228/) (2022)

## Built on by (most cited first, 6 of 6)

- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [Rethinking Mamba in Speech Processing by Self-Supervised Models](https://mlsanity.com/paper/2409.07273/) (2024)
- [Deep Active Speech Cancellation with Mamba-Masking Network](https://mlsanity.com/paper/2502.01185/) (2025)
- [Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation](https://mlsanity.com/paper/2505.16911/) (2025)
- [An overview of neural architectures for self-supervised audio representation learning from masked spectrograms](https://mlsanity.com/paper/2509.18691/) (2025)
- [State Space Models for Bioacoustics: A Comparative Evaluation with Transformers](https://mlsanity.com/paper/2512.03563/) (2025)

## Abstract (arXiv)

In the Sound Event Localization and Detection (SELD) task, Transformer-based models have demonstrated impressive capabilities. However, the quadratic complexity of the Transformer's self-attention mechanism results in computational inefficiencies. In this paper, we propose a network architecture for SELD called SELD-Mamba, which utilizes Mamba, a selective state-space model. We adopt the Event-Independent Network V2 (EINV2) as the foundational framework and replace its Conformer blocks with bidirectional Mamba blocks to capture a broader range of contextual information while maintaining computational efficiency. Additionally, we implement a two-stage training method, with the first stage focusing on Sound Event Detection (SED) and Direction of Arrival (DoA) estimation losses, and the second stage reintroducing the Source Distance Estimation (SDE) loss. Our experimental results on the 2024 DCASE Challenge Task3 dataset demonstrate the effectiveness of the selective state-space model in SELD and highlight the benefits of the two-stage training approach in enhancing SELD performance.