Eleonora Mancini

I am a Research Scientist at Deezer, working on NLP, music information retrieval, and multimodal AI.

I hold a PhD in Computer Science and Engineering - Artificial Intelligence from Alma Mater Studiorum - University of Bologna, specializing in multimodal deep learning and interpretability, with a focus on speech processing, argument mining, clinical decision support, and music information retrieval.

During my PhD, I had the opportunity to work as a visiting researcher at Sony AI Barcelona and MILA - Quebec AI Institute, collaborating on cutting-edge speech and audio technologies. I also gained industry research experience as an AI Research Intern at i2CAT Foundation in Barcelona.

Beyond research, I have teaching experience at the University of Bologna, where I supported courses in AI and Computer Engineering.

My expertise spans multimodal learning, NLP, speech and audio processing, and the medical applications of AI, with a strong commitment to building interpretable, impactful systems.

Research Interests: Multimodal Learning • Music Information Retrieval • NLP • Speech Processing • Interpretability