Timezone: »
Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musicality and realism, so in this work we embark on modelling music in the raw audio domain. It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the expense of modelling long-range correlations. This is problematic because music exhibits structure at many different timescales. In this work, we explore autoregressive discrete autoencoders (ADAs) as a means to enable autoregressive models to capture long-range correlations in waveforms. We find that they allow us to unconditionally generate piano music directly in the raw audio domain, which shows stylistic consistency across tens of seconds.
Author Information
Sander Dieleman (DeepMind)
Aaron van den Oord (Google Deepmind)
Karen Simonyan (DeepMind)
More from the Same Authors
-
2021 : StarCraft II Unplugged: Large Scale Offline Reinforcement Learning »
Michael Mathieu · Sherjil Ozair · Srivatsan Srinivasan · Caglar Gulcehre · Shangtong Zhang · Ray Jiang · Tom Paine · Konrad Żołna · Julian Schrittwieser · David Choi · Petko I Georgiev · Daniel Toyama · Roman Ring · Igor Babuschkin · Timo Ewalds · · Aaron van den Oord · Wojciech Czarnecki · Nando de Freitas · Oriol Vinyals -
2020 : Multi-Format Contrastive Learning of Audio Representations »
Aaron van den Oord -
2020 Poster: Evolving Normalization-Activation Layers »
Hanxiao Liu · Andy Brock · Karen Simonyan · Quoc V Le -
2020 Spotlight: Evolving Normalization-Activation Layers »
Hanxiao Liu · Andy Brock · Karen Simonyan · Quoc V Le -
2020 Poster: Self-Supervised MultiModal Versatile Networks »
Jean-Baptiste Alayrac · Adria Recasens · Rosalia Schneider · Relja Arandjelović · Jason Ramapuram · Jeffrey De Fauw · Lucas Smaira · Sander Dieleman · Andrew Zisserman -
2019 Workshop: NeurIPS Workshop on Machine Learning for Creativity and Design 3.0 »
Luba Elliott · Sander Dieleman · Adam Roberts · Jesse Engel · Tom White · Rebecca Fiebrink · Parag Mital · Christine McLeavey · Nao Tokui -
2019 Poster: Wasserstein Dependency Measure for Representation Learning »
Sherjil Ozair · Corey Lynch · Yoshua Bengio · Aaron van den Oord · Sergey Levine · Pierre Sermanet -
2019 Poster: Large Scale Adversarial Representation Learning »
Jeff Donahue · Karen Simonyan -
2019 Poster: Shaping Belief States with Generative Environment Models for RL »
Karol Gregor · Danilo Jimenez Rezende · Frederic Besse · Yan Wu · Hamza Merzic · Aaron van den Oord -
2019 Poster: Generating Diverse High-Fidelity Images with VQ-VAE-2 »
Ali Razavi · Aaron van den Oord · Oriol Vinyals -
2018 Poster: Learning to Navigate in Cities Without a Map »
Piotr Mirowski · Matt Grimes · Mateusz Malinowski · Karl Moritz Hermann · Keith Anderson · Denis Teplyashin · Karen Simonyan · koray kavukcuoglu · Andrew Zisserman · Raia Hadsell -
2017 Poster: Neural Discrete Representation Learning »
Aaron van den Oord · Oriol Vinyals · koray kavukcuoglu -
2016 Poster: Conditional Image Generation with PixelCNN Decoders »
Aaron van den Oord · Nal Kalchbrenner · Lasse Espeholt · koray kavukcuoglu · Oriol Vinyals · Alex Graves -
2015 Poster: Natural Neural Networks »
Guillaume Desjardins · Karen Simonyan · Razvan Pascanu · koray kavukcuoglu -
2015 Poster: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2015 Spotlight: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2014 Poster: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2014 Spotlight: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2014 Poster: Factoring Variations in Natural Images with Deep Gaussian Mixture Models »
Aaron van den Oord · Benjamin Schrauwen -
2013 Poster: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2013 Spotlight: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2013 Demonstration: Deep Content-Based Music Recommendation »
Aaron van den Oord · Sander Dieleman · Benjamin Schrauwen -
2013 Poster: Deep content-based music recommendation »
Aaron van den Oord · Sander Dieleman · Benjamin Schrauwen