We introduce Jukebox, a model that generates music with singing in the raw audio domain.
We tackle the long context of raw audio using a multiscale VQ-VAE to compress it to discrete …

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 …

Source separation for music is the task of isolating contributions, or stems, from different
instruments recorded individually and arranged together to form a song. Such components …

The design of meaningful audio features is a key need to advance the state-of-the-art in
music emotion recognition (MER). This article presents a survey on the existing emotionally …

Deep neural network based methods have been successfully applied to music source
separation. They typically learn a mapping from a mixture spectrogram to a set of source …

With the emergence of foundation models (FMs) that are trained on large amounts of data at
scale and adaptable to a wide range of downstream applications, AI is experiencing a …

Music source separation has been intensively studied in the last decade and tremendous
progress with the advent of deep learning could be observed. Evaluation campaigns such …

Music source separation involves a large input field to model a long-term dependence of an
audio signal. Previous convolutional neural network (CNN)-based approaches address the …

In this paper, we develop DeepSinger, a multi-lingual multi-singer singing voice synthesis
(SVS) system, which is built from scratch using singing training data mined from music …