Back To Schedule

Overview of Neural Audio Synthesis Algorithms

15:00 - 15:50 UTC | Wednesday 11th November 2026 | Conservatory
Intermediate
Advanced

Neural audio synthesis has seen great progress during the last decade, and currently underpins commercial applications such as text-to-speech synthesis, music generation or neural timbre transfer.

This talk reviews some of the most common building blocks used in neural audio synthesis models, including representation, temporal modelling, generation and conditioning, with an interest in the feasibility of training models on consumer hardware. I will also present an open source library that implements some classic models.

Gerard Roma

Lecturer in Audion Engineering

University of West London

Gerard Roma is a researcher, musician, educator and software developer with an interest in creative applications of digital signal processing and machine learning. He is currently a lecturer in audio engineering at University of West London, where he leads the MSc courses on digital audio engineering and artificial intelligence for sound and music.