Panagiotis Zervas

Panagiotis G. Zervas is Associate Professor in the Department of Electrical and Computer Engineering at the University of Peloponnese and has been a faculty member since 04 June 2020. His field of expertise is technologies for audio signal processing, music information and natural language for knowledge extraction.

Teaching: Signals & Systems, Digital Signal Processing, Statistical Signal Processing & Learning, Audio & Music Technology, Machine Learning, Educational Technology.

Previous Appointments: Assistant Professor, Department of Music Technology and Acoustics, Hellenic Mediterranean University (2015–2020); Assistant Professor, Department of Music Technology and Acoustics, Technological Educational Institute of Crete (2015–2019); Lecturer, Department of Music Technology & Acoustics, Technological Educational Institute of Crete (2008–2015).

PhD (2007): Completed at the Department of Electrical Engineering, University of Patras, on modeling Greek prosody for text-to-speech systems.

Publications & Presentations: Published in leading international journals (e.g. Acoustics, Mathematics) and presented at conferences such as the Web Audio Conference (WAC 2022) and Forum Acusticum 2023.

European Projects: Principal Investigator or Deputy Scientific Coordinator in EU-ALMPO (2025– ), Train4Blue (2025– ), GROWTH4BLUE (2024– ), MICROIDEA (2024– ).

World Bank Collaboration (since 2023): Short-Term Consultant—first (2022–2024) implementing Greece’s National Skills Framework (AI-based skill profiles & employment-monitoring system), then (from 2024) supporting the Pacific Islands Network for Employment with an AI-driven job-and-skills matching portal.

Research Interests

• Natural language applications for text analysis and knowledge extraction;
• large language models for structured-data generation from unstructured input, advanced retrieval-augmented generation and other information-extraction and management techniques;
• audio signal processing and voice analysis;
• music information retrieval using machine learning; embedded systems and IoT with emphasis on intelligent audio applications.