# Vision Transformer Segmentation for Visual Bird Sound Denoising

arXiv: https://arxiv.org/abs/2406.09167 · HTML: https://mlsanity.com/paper/2406.09167/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2024.

## Built on by (most cited first, 2 of 2)

- [Zero-Shot and Supervised Bird Image Segmentation Using Foundation Models: A Dual-Pipeline Approach with Grounding DINO~1.5, YOLOv11, and SAM~2.1](https://mlsanity.com/paper/2603.00184/) (2026)
- [MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control](https://mlsanity.com/paper/2604.00292/) (2026)

## Abstract (arXiv)

Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose ViTVS, a novel approach that leverages the power of the vision transformer (ViT) architecture. ViTVS adeptly combines segmentation techniques to disentangle clean audio from complex signal mixtures. Our key contributions encompass the development of ViTVS, introducing comprehensive, long-range, and multi-scale representations. These contributions directly tackle the limitations inherent in conventional approaches. Extensive experiments demonstrate that ViTVS outperforms state-of-the-art methods, positioning it as a benchmark solution for real-world bird sound denoising applications. Source code is available at: https://github.com/aiai-4/ViVTS.