Audio and machine learning researcher with experience in sound event detection, voice activity detection, privacy-preserving audio, and embedded AI for audio applications. My work combines deep learning, signal processing, and real-world deployment on resource-constrained devices.

As a Research Engineer at the University of Surrey's Centre for Vision, Speech and Signal Processing (CVSSP), I contributed to the EPSRC-funded AI for Sound project, developing AI-driven sound sensing systems, publishing research, building open-source tools, and supervising student projects. I have published at WASPAA, ICASSP, Inter-Noise, CHiME, and SMC, with work spanning speech removal for audio privacy, environmental sound classification on embedded hardware, and soundscape perception.

I work primarily in Python (PyTorch) and have hands-on experience deploying models on edge devices (Raspberry Pi, microcontrollers). My background in electrical engineering (Universidad de la República, Uruguay) gives me a strong foundation in DSP, electronics, and embedded systems. I hold an MSc in Sound and Music Computing from Universitat Pompeu Fabra, where my thesis on harmonic compatibility for DJ software was published by Springer.

Previously, I developed embedded solutions for Bang & Olufsen home automation systems at Ikatu, and held roles at Google (Workspace support) and KPMG (IT audit).

Currently exploring research and R&D opportunities in audio, acoustics, and applied ML. Open to positions in academia, industry research labs, and companies working on sound technology.

Beyond research, I am an electronic music DJ and producer with over a decade of experience, which informs my deep interest in how people perceive and interact with sound.

Email: gabobibbo@gmail.com

Links: [ORCID] | [Scholar] | [Github] | [LinkedIn]