Publications

Research papers and academic contributions in computer vision, machine learning, and natural language processing.

Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System
Hashim Ali, Surya Subramani, Nithin Sai Adupa, Lekha Bollinani, Sali El-loh
IEEE ASRU 2025 (Automatic Speech Recognition and Understanding Workshop)2025Honolulu, Hawaii, USA
Audio DeepfakesSynthetic Speech DetectionText-to-Speech (TTS)Voice Conversion (VC)Multilingual DatasetsAASIST

The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning (SSL) front-ends, training data compositions, and audio length configurations for robust deepfake detection. Our AASIST-based approach incorporates WavLM Large with RawBoost augmentation, trained on a multilingual dataset of 256,600 samples spanning 9 languages and over 70 TTS systems from CodecFake, MLAAD v5, SpoofCeleb, Famous Figures, and MAILABS. Through extensive experimentation with different SSL front-ends, three training data versions, and two audio lengths, we achieved second place in both Task 1 (unmodified audio detection) and Task 3 (laundered audio detection), demonstrating strong generalization and robustness.

One-class classification for Speaker-Specific Audio Spoof Detection
Hashim Ali, Surya Subramani, Nithin Sai Adupa, Lekha Bollinani, Sali El-loh
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)2025Tahoe City, California, USA
Audio DeepfakesSpeech Spoofing DetectionText-to-Speech (TTS)Voice Conversion (VC)Self-Supervised Learning (SSL)One-Class Classification

This paper introduces a speaker-specific framework for detecting audio deepfakes. By combining self-supervised learning embeddings with a one-class SVM trained only on genuine speech, the method reliably identifies synthetic voices. Evaluations on benchmark and real-world datasets show strong performance across diverse spoofing techniques, making it a practical solution for safeguarding individuals, such as political figures, against audio impersonation.

μTESLA 3: Mechanisms of Surface Texture Enhanced Boundary Layer Pump
Rohma Rizvi, Sali El-loh, Siyu Chen, Kai Duan, Joe F. Lo
µTAS 2021 (International Conference on Miniaturized Systems for Chemistry and Life Sciences)2021Palm Springs, California, USA
μTesla RotorMicrofluidicsSurface Texture EngineeringBoundary Layer FlowPump PerformanceFluid DynamicsExperimental ValidationComputational Fluid Dynamics (CFD)

This paper investigates how surface texture influences the performance of the μTesla rotor version 3. By varying the amplitude and frequency of sinusoidal textures on the rotor surfaces, the authors demonstrate that the boundary layer flow and pump output can be effectively controlled, as confirmed through simulations and experimental measurements