4 papers · 1 filter
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…
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…
Quantum-Inspired Genetic Algorithm for Robust Source Separation in Smart City Acoustics
Minh K. Quan, Mayuri Wijayasundara, Sujeeva Setunge +1
The cacophony of urban sounds presents a significant challenge for smart city applications that rely on accurate acoustic scene analysis. Effectively analyzing these complex sounds…