New methods for modeling musical scores, often based on deep learning, have made it possible to automatically generate ever more convincing compositions. However, these models are often not accessible enough for artists to easily play and experiment with on their own terms. Application developers are already imagining ways to apply their design expertise to this new class of AI technologies but often lack a sufficient background in machine learning. Magenta.js is a new open source library with a simple JavaScript API intended to bridge this gap by abstracting away technical details, making it easier than ever for app developers to create new interfaces to generative models. Furthermore, because it is easily extensible, we hope that Magenta.js can foster a connection between the broader research community and creative developers through contributions from both groups. Finally, Magenta.js will open up the possibility for a new type of compositional tool that adapts to user preferences and behaviors in real-time. Code and documentation are available online at https://goo.gl/magenta/js.
[1]
Shan Carter,et al.
Using Artificial Intelligence to Augment Human Intelligence
,
2017
.
[2]
Peter M. Todd,et al.
A Connectionist Approach To Algorithmic Composition
,
1989
.
[3]
Michael C. Mozer,et al.
Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing
,
1994,
Connect. Sci..
[4]
Douglas Eck,et al.
Learning via social awareness: improving sketch representations with facial feedback
,
2018,
ICLR.
[5]
Colin Raffel,et al.
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
,
2018,
ICML.
[6]
Gaëtan Hadjeres,et al.
Deep Learning Techniques for Music Generation - A Survey
,
2017,
ArXiv.
[7]
Jürgen Schmidhuber,et al.
Finding temporal structure in music: blues improvisation with LSTM recurrent networks
,
2002,
Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.