|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
This repository contains the model checkpoints related to the paper: [Less is More for Synthetic Speech Detection in the Wild](https://arxiv.org/abs/2502.05674) |
|
|
|
Dataset can be downloaded from [here](https://huggingface.co/datasets/ash56/ShiftySpeech/tree/main) |
|
|
|
## 🔥 Key Features |
|
- 3000+ hours of synthetic speech |
|
- **Diverse Distribution Shifts**: The dataset spans **7 key distribution shifts**, including: |
|
- 📖 **Reading Style** |
|
- 🎙️ **Podcast** |
|
- 🎥 **YouTube** |
|
- 🗣️ **Languages (Three different languages)** |
|
- 🌎 **Demographics (including variations in age, accent, and gender)** |
|
- **Multiple Speech Generation Systems**: Includes data synthesized from various **TTS models** and **vocoders**. |
|
|
|
## 💡 Why We Built This Dataset |
|
> Driven by advances in self-supervised learning for speech, state-of-the-art synthetic speech detectors have achieved low error rates on popular benchmarks such as ASVspoof. However, prior benchmarks do not address the wide range of real-world variability in speech. Are reported error rates realistic in real-world conditions? To assess detector failure modes and robustness under controlled distribution shifts, we introduce **ShiftySpeech**, a benchmark with more than 3000 hours of synthetic speech from 7 domains, 6 TTS systems, 12 vocoders, and 3 languages. |
|
> |
|
🚀 **Stay tuned! More model checkpoints will be available soon.** |
