people

I mainly supervise Master theses focusing on the application of generative models to music or synthesis. I also supervised works related to spatial audio. If you are interested in discussing a master thesis or in different types of collaborations feel free to write me an email!

Currently supervised theses

• Alice Portentoso [Music Machine Unlearning] (Co-advisor Francesca Ronchini, Paolo Bestagini)
• Flavio Ingenito [Shapley values applied to text-to-music models] (Co-advisor Francesca Ronchini, Paolo Bestagini)
• Riccardo Moschen [Interaction Design for live performance of acousmatic music_] (Co-advisor Francesca Ronchini, Massimo Colombo) @[INNER_SPACES]

Past Supervised theses

• Francisco Messina [Towards Memorization Free Audio Diffusion Models] (Co-advisor Francesca Ronchini, Paolo Bestagini)
• Alice Lenoci [Towards Black-Box Membership Inference in Diffusion-Based Music Generative Models] (Co-advisor Francesca Ronchini, Paolo Bestagini)
• Sophia Barbera [Fake music detection with open-set recognition and vocal-instrumental separation] (Co-advisor Francesca Ronchini, Paolo Bestagini)
• Wenjia Luo Beyond the Console: A Gesture-Driven Mobile Spatial Audio System in Cross-Domain Collaboration (Co-advisor Francesca Ronchini, Massimo Colombo) @INNER_SPACES)
• Federico Angelo Luigi Ruggeri Sound Event Detection and Localization using Mel-FSGCC (Co-advisor Francesca Ronchini, Prof. Maximo Cobos)
• Simone Marcucci Text-to-music models for creative music practice: a user experience study (Co-advisor Francesca Ronchini)
• Riccardo Passoni Balance between performance end carbon footspring of state-of-the-art deep learning systems for audio domain applications (Co-advisor Francesca Ronchini, Prof. Romain Serizel)
• Guglielmo Fraticcioli Timbre Transfer using selective state-space models (Co-advisor Francesca Ronchini)
• Nicolò Pisanu Bioacustic event detection using deep learning (@GemmoAI)
• Marco Furio Colombo Mamba-Foley: Time-Controlled Foley Sound Generation using Selective State-Space Models (Co-advisor Francesca Ronchini)

Past Co-supervised theses

• Juan Camilo Albarracín Sánchez HRTF personalization based on denoising diffusion models (Advisor Dr. Mirco Pezzoli) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2023/2024

• Gabriele Perego Prompt Audio Generator User Research Investigation, M.Sc. Thesis in Music and Acoustic Engineering, (Co-advisor Francesca Ronchini, Advisor Dr. Massimiliano Zanoni) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2021/2022

• Gabriele Maucione A study on the effect of dynamic accents on the perception and measurement of rhythm complexity (co-advisor Alessandro Ilic Mezza, advisor Prof. Augusto Sarti) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2022/2023

• Francesco Zumerle Procedural Music Generation For Video games (advisor Dr. Massimiliano Zanoni) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2022/2023

• Roberto Alessandri A deep learning-based method for multi-zone sound field synthesis (advisor Prof. Fabio Antonacci) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2021/2022

• Silvio Pol Timbre Transfer and Interpolation Using a Conditional Convolutional beta-Variational Autoencoder(advisor Dr. Massimiliano Zanoni) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2021/2022

• Federico Miotello A deep prior approach to inpainting of audio signals (advisor Prof. Fabio Antonacci, co-advisor Dott. Mirco Pezzoli.) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2020/2021

• Davide Mori Towards soundfield rendering with distributed loudspeaker arrays using convolutional neural networks applied to the ray space transform (advisor Prof. Fabio Antonacci) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2019/2020

• Davide Gioiosa Modeling harmonic complexity in automatic music generation using conditional variational autoencoders (advisor Dr. Massimiliano Zanoni) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2019/2020

• Alessandro Montali Interpreting deep neural networks models for acoustic source localization using layer-wise relevance propagation (advisor Prof. Fabio Antonacci) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2019/2020

• Matteo Manzolini Cellular music : a novel music-generation platform based on an evolutionary paradigm (advisor Prof. Augusto Sarti, co-advisor Dr. Clara Borrelli.) M.Sc. in Music and Acoustic Engineering, Politecnico di Milano AA 2019/2020

• Minh Cèdric Schils Audio frame reconstruction from incomplete observations using Deep Learning techniques, (advisors Prof. Augusto Sarti, Prof. Jean-Jacques Embrechts.) Master en ingénieur civil en informatique, à finalité spécialisée en “intelligent systems”, Université de Liège, AA 2019/2020

• Riccardo Battello Techniques for mitigating the impact of latency in networked music performance (NMP) through adaptive metronomes (advisor Prof. Augusto Sarti) M.Sc. in Computer Science and Engineering, Politecnico di Milano AA 2018/2019