Khaled Koutini

Khaled Koutini is a Post-Doctoral Researcher at the Institute of Computational Perception, Johannes Kepler University Linz. His research focuses on developing general-purpose audio representations using deep neural networks, addressing challenges in audio classification, tagging, and machine listening. He investigates inductive biases in neural architectures and training processes to enhance generalization on small datasets, as well as transfer learning from large-scale models to specialized tasks.

• Affiliation: Institute of Computational Perception, JKU Linz
• Supervisor of PhD project: Gerhard Widmer
• PhD project period: January 2020 – Ongoing

His work spans applications in content-based multimedia retrieval, context-aware devices, and environmental monitoring systems. The research emphasizes overcoming data scarcity issues in machine audio recognition.