---
license: mit
datasets:
- nuriachandra/Deepfake-Eval-2024
- jungjee/spoofceleb
---

# WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection

Official PyTorch implementation: https://github.com/xxuan-acoustics/WaveSP-Net

### How to Use

```bash
# pip install torch torchaudio huggingface_hub soundfile
import torch, torchaudio
from huggingface_hub import hf_hub_download
from model import WaveSPNet

ckpt_path = hf_hub_download(repo_id="xxuan-speech/WaveSP-Net",
                            filename="WaveSP-Net.pt")
```

### BibTeX

```bash
@inproceedings{xuan2025wavesp,
  title={WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection},
  author={Xi Xuan and Xuechen Liu and Wenxin Zhang and Yi-Cheng Lin and Xiaojian Lin and Tomi Kinnunen},
  booktitle={ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2026},
  organization={IEEE}
}

```