T7.1: Advanced digitisation, datasets acquisition, and reuse (Lead: IHU; Contributors: All; [M19-M28]) – T7.1 will focus on the development of TK1, TK2, and TK3. The methodologies that will be applied are M1.2.1.1, M1.2.1.2 and M1.2.1.3. More specific, the task will develop cutting-edge techniques for capturing and processing high-resolution digital representations of musical cultural heritage (CH) artifacts. This will involve the use of advanced technologies, such as 3D scanning, acoustic profiling, and material analysis, to create detailed, accurate digital models of historical instruments and acoustic spaces. These digital representations encompass both the physical and acoustic characteristics of the artifacts, providing a comprehensive record for preservation and restoration purposes. (Output: D7.1). 

T7.2: Advanced AI for dynamic digitisation in acoustics and musical CH (Lead: UMA; Contributors: IHU, FH, TUIL, BEN#7, SCHUM, LUTHI; [M19-M32]) – This task focuses on the development of the first versions for TK3, TK4, TK5 and TK9. The methodologies that will be applied are M1.2.1.1, M1.2.1.3, M1.2.1.6 and M1.2.1.7. More specific, the task will focus on applying cutting-edge artificial intelligence (AI) technologies to enhance the real-time digitization and analysis of musical artifacts. By integrating machine learning and deep learning techniques, this approach enables the creation of highly accurate, adaptive digital representations that capture both the acoustic and material properties of musical heritage, detecting subtle changes in the artifacts’ condition over time, offering predictive insights into their evolution and degradation. Furthermore, AI will optimize the digitization process, making it more efficient and scalable, while supporting interactive, immersive experiences for users. (Output: D7.2).

T7.3: Advanced AI for monitoring the evolution of musical CH (Lead: TUIL; Contributors: IHU, UMA, BEN#7, SCHUM, LUTHI; [M19-M32]) – This task focuses on the development of TK4 and TK5. The methodologies that will be applied are M1.2.1.4 and M1.2.1.5. More specific, the task will apply sophisticated artificial intelligence techniques to track and predict the ongoing changes in the physical, material, and acoustic properties of musical heritage artifacts over time. By utilizing predictive modelling and machine learning algorithms, this approach will enable continuous monitoring of artifacts, identifying subtle shifts in their condition that may not be immediately apparent. AI models will analyse data from different factors to forecast future degradation or changes, allowing for proactive conservation strategies.(Output: D7.2).

T7.4: Advanced AI for improved interaction in acoustics and musical CH (Lead: FH; Contributors: All; [M19-M32]) – This task focuses on the development of the first versions for TK6, TK7, TK8 and TK9. The methodologies that will be applied are M1.2.1.7 and M1.2.1.8. More specific, the task will enhance user engagement with musical heritage through personalized, immersive experiences. AI-driven real-time acoustic analysis adapts interactions with historical instruments and acoustic spaces based on user preferences. By integrating cross-modal elements (sound, touch, and visuals), AI enables dynamic virtual environments for interaction with recreated instruments and soundscapes. Additionally, adaptive learning systems provide personalized feedback, guiding users through historical contexts and techniques. This AI application transforms how users experience, learn, and engage with musical cultural heritage, making it more accessible and impactful. (Output: D7.2).