AI (r)evolution -- where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning

no code implementations • 20 Sep 2023 • Giovanni Bindi, Nils Demerlé, Rodrigo Diaz, David Genova, Aliénor Golvet, Ben Hayes, Jiawen Huang, Lele Liu, Vincent Martos, Sarah Nabi, Teresa Pelinski, Lenny Renault, Saurjya Sarkar, Pedro Sarmento, Cyrus Vahidi, Lewis Wolstanholme, Yixiao Zhang, Axel Roebel, Nick Bryan-Kinns, Jean-Louis Giavitto, Mathieu Barthet

The students represent the future generation of AI and music researchers.

The Responsibility Problem in Neural Networks with Unordered Targets

no code implementations • 19 Apr 2023 • Ben Hayes, Charalampos Saitis, György Fazekas

We discuss the discontinuities that arise when mapping unordered objects to neural network outputs of fixed permutation, referred to as the responsibility problem.

Rigid-Body Sound Synthesis with Differentiable Modal Resonators

1 code implementation • 27 Oct 2022 • Rodrigo Diaz, Ben Hayes, Charalampos Saitis, György Fazekas, Mark Sandler

Physical models of rigid bodies are used for sound synthesis in applications from virtual environments to music production.

Sinusoidal Frequency Estimation by Gradient Descent

1 code implementation • 26 Oct 2022 • Ben Hayes, Charalampos Saitis, György Fazekas

Sinusoidal parameter estimation is a fundamental task in applications from spectral analysis to time-series forecasting.

Time Series Time Series Forecasting

Neural Waveshaping Synthesis

1 code implementation • 11 Jul 2021 • Ben Hayes, Charalampos Saitis, György Fazekas

We present the Neural Waveshaping Unit (NEWT): a novel, lightweight, fully causal approach to neural audio synthesis which operates directly in the waveform domain, with an accompanying optimisation (FastNEWT) for efficient CPU inference.

Audio Generation Audio Synthesis