Nizar Bouguila

Learnable Wavelet-Enhanced Bidirectional Autoencoders: A Unified Framework for Multi-Resolution Speech Enhancement

Geometry-Aware Generative Modeling for Graph Clustering via Hyperspherical Diffusion

Learnable Fractional Superlets with a Spectro-Temporal Emotion Encoder for Speech Emotion Recognition

Smoothed-ModernBERT: Co-Attentional Synergy of Probabilistic Topic Models and ModernBERT through Dynamic Fusion