# SynHate: Detecting Hate Speech in Synthetic Deepfake Audio

arXiv: https://arxiv.org/abs/2506.06772 · HTML: https://mlsanity.com/paper/2506.06772/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2025.

## Built on by (most cited first, 3 of 3)

- [Ethical and Technical Limits of Deepfake Speech Datasets](https://mlsanity.com/paper/2606.10911/) (2026)
- [Zero-Shot to Zero-Lies: Detecting Bengali Deepfake Audio through Transfer Learning](https://mlsanity.com/paper/2512.21702/) (2025)
- [Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages](https://mlsanity.com/paper/2604.09094/) (2026)

## Abstract (arXiv)

The rise of deepfake audio and hate speech, powered by advanced text-to-speech, threatens online safety. We present SynHate, the first multilingual dataset for detecting hate speech in synthetic audio, spanning 37 languages. SynHate uses a novel four-class scheme: Real-normal, Real-hate, Fake-normal, and Fake-hate. Built from MuTox and ADIMA datasets, it captures diverse hate speech patterns globally and in India. We evaluate five leading self-supervised models (Whisper-small/medium, XLS-R, AST, mHuBERT), finding notable performance differences by language, with Whisper-small performing best overall. Cross-dataset generalization remains a challenge. By releasing SynHate and baseline code, we aim to advance robust, culturally sensitive, and multilingual solutions against synthetic hate speech. The dataset is available at https://www.iab-rubric.org/resources.