no code implementations • 30 Jan 2023 • Chris Donahue, Antoine Caillon, Adam Roberts, Ethan Manilow, Philippe Esling, Andrea Agostinelli, Mauro Verzetti, Ian Simon, Olivier Pietquin, Neil Zeghidour, Jesse Engel
We present SingSong, a system that generates instrumental music to accompany input vocals, potentially offering musicians and non-musicians alike an intuitive new way to create music featuring their own voice.
3 code implementations • 26 Jan 2023 • Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Christian Frank
We introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff".
Ranked #9 on Text-to-Music Generation on MusicCaps
no code implementations • 14 Apr 2022 • Antoine Caillon, Philippe Esling
As our method is based on a post-training reconfiguration of the model, we show that it is able to transform models trained without causal constraints into a streaming model.
1 code implementation • 9 Nov 2021 • Antoine Caillon, Philippe Esling
By leveraging a multi-band decomposition of the raw waveform, we show that our model is the first able to generate 48kHz audio signals, while simultaneously running 20 times faster than real-time on a standard laptop CPU.
no code implementations • 4 Aug 2020 • Antoine Caillon, Adrien Bitton, Brice Gatinet, Philippe Esling
Recent studies show the ability of unsupervised models to learn invertible audio representations using Auto-Encoders.
1 code implementation • 31 Jul 2020 • Philippe Esling, Ninon Devis, Adrien Bitton, Antoine Caillon, Axel Chemla--Romeu-Santos, Constance Douwes
This hypothesis states that extremely efficient small sub-networks exist in deep models and would provide higher accuracy than larger models if trained in isolation.
3 code implementations • 12 Apr 2019 • Adrien Bitton, Philippe Esling, Antoine Caillon, Martin Fouilleul
Its training data subsets can directly be visualized in the 3D latent representation.