17 papers
Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning
Bipasha Kashyap, Björn W. Schuller, Pubudu N. Pathirana
Speech signals encode emotional, linguistic, and pathological information within a shared acoustic channel; however, disentanglement is typically assessed indirectly through downst…
Certified Causal Attribution for Real-Time Attack Forensics in 6G Network Slicing
Minh K. Quan, Pubudu N. Pathirana
Cross-slice attack attribution in 6G networks requires identifying causal propagation chains through shared infrastructure in under 100 ms. Existing methods struggle to satisfy thi…
StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splitting
Minh K. Quan, Pubudu N. Pathirana
Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource constraints of edge devices. This…
Geometric Analysis of Speech Representation Spaces: Topological Disentanglement and Confound Detection
Bipasha Kashyap, Pubudu N. Pathirana
Speech-based clinical tools are increasingly deployed in multilingual settings, yet whether pathological speech markers remain geometrically separable from accent variation remains…
Quantifying Quanvolutional Neural Networks Robustness for Speech in Healthcare Applications
Ha Tran, Bipasha Kashyap, Pubudu N. Pathirana
Speech-based machine learning systems are sensitive to noise, complicating reliable deployment in emotion recognition and voice pathology detection. We evaluate the robustness of a…
Leveraging Vision Transformers for Enhanced Classification of Emotions using ECG Signals
Pubudu L. Indrasiri, Bipasha Kashyap, Pubudu N. Pathirana
Biomedical signals provide insights into various conditions affecting the human body. Beyond diagnostic capabilities, these signals offer a deeper understanding of how specific org…