State Space Models for Bioacoustics: A comparative Evaluation with Transformers

• URL: http://arxiv.org/abs/2512.03563v1
• Date: Wed, 03 Dec 2025 08:37:09 GMT
• Title: State Space Models for Bioacoustics: A comparative Evaluation with Transformers
• Abstract summary: We first pretrain a Mamba-based audio large language model (LLM) on a large corpus of audio data using self-supervised learning.<n>We fine-tune and evaluate BioMamba on the BEANS benchmark, a collection of diverse bioacoustic tasks including classification and detection.<n>The results show that BioMamba achieves comparable performance with AVES while consumption significantly less VRAM.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this study, we evaluate the efficacy of the Mamba model in the field of bioacoustics. We first pretrain a Mamba-based audio large language model (LLM) on a large corpus of audio data using self-supervised learning. We fine-tune and evaluate BioMamba on the BEANS benchmark, a collection of diverse bioacoustic tasks including classification and detection, and compare its performance and efficiency with multiple baseline models, including AVES, a state-of-the-art Transformer-based model. The results show that BioMamba achieves comparable performance with AVES while consumption significantly less VRAM, demonstrating its potential in this domain.

Related papers

• Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds [24.203596224724848]
  Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored.<n>We show that models such as HuBERT, WavLM, and XEUS can generate rich latent representations of animal sounds across taxa.<n>Results are competitive with fine-tuned bioacoustic pre-trained models and show the impact of noise-robust pre-training setups.
  arXiv  Detail & Related papers  (2025-09-04T12:39:05Z)
• Foundation Models for Bioacoustics -- a Comparative Review [0.9109149174920012]
  We review bioacoustic foundation models by thoroughly analysing design decisions such as model architecture, pretraining scheme, and training paradigm.<n>We evaluate selected foundation models on classification tasks from the BEANS and BirdSet benchmarks.<n>Our comprehensive experimental analysis reveals that BirdMAE, trained on large-scale bird song data with a self-supervised objective, achieves the best performance on the BirdSet benchmark.
  arXiv  Detail & Related papers  (2025-08-02T09:15:16Z)
• An Exploration of Mamba for Speech Self-Supervised Models [48.01992287080999]
  We explore Mamba-based HuBERT models as alternatives to Transformer-based SSL architectures.<n>HuBERT models enable fine-tuning on long-context ASR with significantly lower compute.<n>These findings highlight Mamba-based SSL as a promising and complementary direction for long-sequence modeling, real-time speech modeling, and speech unit extraction.
  arXiv  Detail & Related papers  (2025-06-14T19:00:44Z)
• MambaMoE: Mixture-of-Spectral-Spatial-Experts State Space Model for Hyperspectral Image Classification [46.67137351665963]
  Mamba-based models have recently demonstrated significant potential in hyperspectral image (HSI) classification.<n>We propose MambaMoE, a novel spectral-spatial Mixture-of-Experts (MoE) framework, which represents the first MoE-based approach in the HSI classification domain.<n>MambaMoE achieves state-of-the-art performance in both classification accuracy and computational efficiency compared to existing advanced methods.
  arXiv  Detail & Related papers  (2025-04-29T07:50:36Z)
• BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classification [1.9414307529560617]
  Existing methods for biosignal classification rely on Attention-based frameworks with dense Feed Forward layers.<n>By integrating these three key components, BioMamba effectively addresses the limitations of existing methods.<n>Extensive experiments demonstrate that BioMamba significantly outperforms state-of-the-art methods with marked improvement in classification performance.
  arXiv  Detail & Related papers  (2025-03-14T16:42:58Z)
• ReMamba: Equip Mamba with Effective Long-Sequence Modeling [50.530839868893786]
  We propose ReMamba, which enhances Mamba's ability to comprehend long contexts.<n>ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process.
  arXiv  Detail & Related papers  (2024-08-28T02:47:27Z)
• MambaVision: A Hybrid Mamba-Transformer Vision Backbone [54.965143338206644]
  We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications.<n>We show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies.<n>For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput.
  arXiv  Detail & Related papers  (2024-07-10T23:02:45Z)
• Vision Mamba for Classification of Breast Ultrasound Images [9.90112908284836]
  Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) using the breast ultrasound BUSI dataset and Breast Ultrasound B dataset.
  arXiv  Detail & Related papers  (2024-07-04T00:21:47Z)
• Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining [85.08169822181685]
  This paper introduces a novel Mamba-based model, Swin-UMamba, designed specifically for medical image segmentation tasks. Swin-UMamba demonstrates superior performance with a large margin compared to CNNs, ViTs, and latest Mamba-based models.
  arXiv  Detail & Related papers  (2024-02-05T18:58:11Z)
• Improving Biomedical Entity Linking with Retrieval-enhanced Learning [53.24726622142558]
  $k$NN-BioEL provides a BioEL model with the ability to reference similar instances from the entire training corpus as clues for prediction. We show that $k$NN-BioEL outperforms state-of-the-art baselines on several datasets.
  arXiv  Detail & Related papers  (2023-12-15T14:04:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.