We tackle the task of conditional music generation. We introduce MusicGen, a single
Language Model (LM) that operates over several streams of compressed discrete music …

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural
networks. It consists in a streaming encoder-decoder architecture with quantized latent …

We present a causal speech enhancement model working on the raw waveform that runs in
real-time on a laptop CPU. The proposed model is based on an encoder-decoder …

We present and release a new tool for music source separation with pre-trained models
called Spleeter. Spleeter was designed with ease of use, separation performance, and …

Source separation models either work on the spectrogram or waveform domain. In this work,
we show how to perform end-to-end hybrid source separation, letting the model decide …

A natural question arising in Music Source Separation (MSS) is whether long range
contextual information is useful, or whether local acoustic features are sufficient. In other …

The performance of music source separation (MSS) models has been greatly improved in
recent years thanks to the development of novel neural network architectures and training …

Diffusion models have recently shown promising results for difficult enhancement tasks such
as the conditional and unconditional restoration of natural images and audio signals. In this …

We present a new method for separating a mixed audio sequence, in which multiple voices
speak simultaneously. The new method employs gated neural networks that are trained to …

In this paper, we present an efficient neural network for end-to-end general purpose audio
source separation. Specifically, the backbone structure of this convolutional network is the …