Giampiero Salvi

Giampiero Salvi is a Professor at the Department of Electronic Systems, Norwegian University of Science and Technology (NTNU). He is affiliated with the Signal Processing research group and holds academic qualifications from La Sapienza University of Rome (Civil Engineering) and the Royal Institute of Technology (Dr.Scient). His research focuses on artificial intelligence, machine learning, speech processing, and human-machine interaction. Key contributions include advancements in speech recognition systems, neural network architectures for video prediction, and applications in healthcare analytics and cybersecurity.

His work bridges theoretical foundations with practical implementations, such as developing pronunciation assessment frameworks for children, Parkinson’s disease detection via speech analysis, and real-time speaker diarization systems. He has contributed to foundational research in acoustic-to-articulatory mapping, explainable AI for clinical prediction, and multimodal dialogue systems. His research often addresses challenges in low-resource languages and clinical settings, emphasizing interdisciplinary collaboration.

Salvi’s recent publications highlight trends in foundational models, generative AI for video and speech, and ethical AI applications in healthcare. He actively participates in international conferences and collaborates with institutions like KTH Royal Institute of Technology and the University of Tartu, reflecting his global academic network.