MediaLab presents the research and activities of the Department of Speech, Media and Content Technologies at the Institute for Language and Speech Processing (ILSP), Athena Research Center. Our work spans speech and language technologies, music and audio, intelligent multimedia, and digital cultural heritage, with applications in education, accessibility, health and the creative industries.
Speech and Language Technologies
Speech analysis, recognition and synthesis, expressive and spontaneous speech, spoken interaction and multimodal communication are central to the department’s research. Work on language models and multilingual content connects this expertise with education, accessibility and domain-specific applications.
Department members Georgios Paraskevopoulos, Athanasios Katsamanis and Vassilis Katsouros contributed to Krikri: Advancing Open Large Language Models for Greek (Findings of EMNLP 2025), together with colleagues across ILSP. This collaboration advances open language models for Greek.
Through ILSP’s participation in PHAROS – The Greek AI Factory (April 2025–March 2028), with Vassilis Katsouros as the ILSP project leader, the department contributes to a national partnership supporting AI research and innovation, including culture and language. PHAROS brings together multiple institutions and partners.
Examples include PLan-V (2020–2023), which developed a virtual assistant for people with speech impairments, and DataTools4Heart (2022–2025), addressing multilingual clinical information and AI tools for cardiology.
Music and Audio Intelligence
Research in audio and music processing supports personalised recommendation, interactive learning and creative collaboration. The portfolio includes i-MRePlay (2022–2025), ΕπιSTEAMουσική (2021–2024) and iMuSciCA (2017–2019). These projects connect signal processing, machine learning and music with human-centred applications.
Multimedia, Heritage and Interaction
3D Digitisation and Digital Heritage
High-quality 2D/3D digitisation, 3D reconstruction, photogrammetry, scanning, multispectral recording and workflows for cultural heritage documentation.
Digital Twins for Cultural Heritage
Reactive and diagnostic digital twins for monuments, sites and cultural assets, combining sensing, imaging, semantics and AI-supported monitoring.
Intelligent Multimedia and AI
Machine learning, multimodal analysis, computer vision, metadata enrichment, content-based retrieval and AI-supported interpretation of complex media.
Virtual Museums, XR and Interaction
Interactive 3D environments, virtual exhibitions, augmented and virtual reality, visitor experiences and creative applications for culture, education and tourism.
Accessibility and Inclusive Cultural Content
Technologies that make cultural heritage and multimedia content more accessible, including inclusive interaction, assistive cultural experiences and educational applications.
Recent Activity
The research themes above are reflected in the lab’s project portfolio, recent project news and publication record. See Projects, Publications and Media for examples, demos and public-facing material.