Publications

Thirulok Sundar Mohan Rasu, Aswin Suresh, Arun Balajee Vasudevan

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025

We propose a content-agnostic deepfake speech detection model trained on a curated dataset of 1M+ real-fake speech pairs. By using transcripts from real speech to generate synthetic audio using cutting-edge TTS systems (YourTTS, XTTS-v2, OpenVoice), we eliminate linguistic cues and force the model to rely solely on acoustic artifacts. Our model achieves superior performance compared to prior work and outperforms human listeners across all speech lengths.

@inproceedings{mohanrasu2025deepfake,
  title={Towards Content-Agnostic Deepfake Speech Detection with Multi-TTS},
  author={Mohan Rasu, Thirulok Sundar and Suresh, Aswin and Vasudevan, Arun Balajee},
  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2025}
}

Thirulok Sundar Mohan Rasu

Analyzed failure cases of MASt3R for multi-view reconstruction under challenging capture conditions. Collected a small scene dataset and documented limitations of current state-of-the-art methods.