Publications

Thirulok Sundar, Jiawei Zhang, Ziyou Song

Draft in preparation

A hybrid EIS model coupling a physics-based transmission-line SEI impedance formulation with a compact ECM representation. Degradation-aware constraints embedded in a differential evolution optimizer enforce monotonic SEI growth from BOL to EOL. Validated on 6 commercial Li-ion cells across multiple SOC levels, yielding 1.7% MAP error. OAT sensitivity analysis identifies L_SEI and σ_SEI as the dominant parameters governing the high-frequency SEI arc.

Thirulok Sundar Mohan Rasu, Aswin Suresh, Arun Balajee Vasudevan

Submitted to Interspeech 2026

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.