WhoBuilt

Key facts

Built by
Capabilities
uses deep learning models to generate new sounds

Timeline 2

Dated events, newest first. Open the sources under any item.

How we verify
Built1Capability1
20172 events
  1. as of Jul 2017Capability
    Uses deep learning models to generate new sounds
    “trying to get deep learning models to generate new sounds” 2:42
    Unverified1 source· Talk
  2. as of Jul 2017Built
    Magenta built NSynth
    “We have this project called NSynth” 2:42
    Unverified1 source· Talk

Talks 1

44:21
Making Music and Art Through Machine Learning

Doug Eck describes Magenta’s work on open source machine learning tools for music and art, including sound generation with NSynth and sketch generation with SketchRNN. He explains why current models can produce interesting, imperfect results, and how artists can use those results as material to explore rather than as finished work. The talk covers challenges in evaluating generated media, improving tools for musicians, and using reinforcement learning rewards to steer generative models. Eck argues that machine learning is best treated as part of a creative toolkit, with people shaping how it is used.

Jul 21, 2017· 44 minDiscussed 2:42