arxivst stuff from arxiv that you should probably bookmark

Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders

Abstract · Apr 5, 2017 06:34 ·

cs-lg cs-ai cs-sd

Arxiv Abstract

  • Jesse Engel
  • Cinjon Resnick
  • Adam Roberts
  • Sander Dieleman
  • Douglas Eck
  • Karen Simonyan
  • Mohammad Norouzi

Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio modeling. First, we detail a powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform. Second, we introduce NSynth, a large-scale and high-quality dataset of musical notes that is an order of magnitude larger than comparable public datasets. Using NSynth, we demonstrate improved qualitative and quantitative performance of the WaveNet autoencoder over a well-tuned spectral autoencoder baseline. Finally, we show that the model learns a manifold of embeddings that allows for morphing between instruments, meaningfully interpolating in timbre to create new types of sounds that are realistic and expressive.

Read the paper (pdf) »