I am currently part of the EPSRC funded Centre for Doctoral Training in Intelligent Games and Game Intelligence, based in York, UK. From 2018 and in collaboration with Sony Interactive Entertainment Europe, I am researching about strategies to increase the efficiency in the creation of procedural audio models for video games by using DSP and machine learning approaches.
My main research interests, applied to the synthesis of sound effects, are:
- Generative deep learning (GANs, RNNs and VAEs) to synthesise raw audio.
- Machine learning to find out the best parameters for a synthesiser to generate a target sound.
- Game audio and procedural sound design.
- Real-time audio programming (C/C++, Faust, ChucK, Pure Data…).
- Machine learning and generative deep learning.
- Digital signal processing.
- Game Development (Unity, Unreal).
I have been enthusiastic about sound and more specifically about game audio since I began my studies. By the time I completed my HND in Creative Media Production in Madrid, I started working in the industry as a recording engineer in an ADR studio for the Spanish localisation of video games (such as Fallout 4, Until Dawn or Just Cause 3). I moved from Spain to the UK in 2015 to take a BA (top-up) in Music Production at the Southampton Solent University and an MSc in Sound Design at the University of Edinburgh immediately after. During that journey, I focused my career in procedural audio and explored ways to create models for interactive applications by using different techniques.