2 papers
cs.LG2026
Shortcut Learning in Binary Classifier Black Boxes: Applications to Voice Anti-Spoofing and Biometrics
Md Sahidullah, Hye-jin Shim, Rosa Gonzalez Hautamäki +1
The widespread adoption of deep-learning models in data-driven applications has drawn attention to the potential risks associated with biased datasets and models. Neglected or hidd…
eess.AS2025
Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
Jagabandhu Mishra, Manasi Chhibber, Hye-jin Shim +1
We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional counterme…