This repository contains the model checkpoints related to the paper: Less is More for Synthetic Speech Detection in the Wild

Dataset can be downloaded from here

Checkpoints can be used in complementary to the official GitHub repository.

🚀 Stay tuned! Hugging Face support for loading the model will be added soon.

If you find the dataset or this resource helpful for your research, please cite our work:

@misc{garg2025syntheticspeechdetectionwild,
      title={Less is More for Synthetic Speech Detection in the Wild}, 
      author={Ashi Garg and Zexin Cai and Henry Li Xinyuan and Leibny Paola García-Perera and Kevin Duh and Sanjeev Khudanpur and Matthew Wiesner and Nicholas Andrews},
      year={2025},
      eprint={2502.05674},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2502.05674}, 
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.