Timezone: »

Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Cinjon Resnick · Adam Roberts · Jesse Engel · Douglas Eck · Sander Dieleman · Karen Simonyan · Mohammad Norouzi

Mon Aug 07 09:42 PM -- 10:00 PM (PDT) @ Parkside 1

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.

Author Information

Cinjon Resnick (Google Brain)
Adam Roberts (Google Brain)
Jesse Engel (Google Brain)
Douglas Eck (Google Brain)
Sander Dieleman (DeepMind)
Karen Simonyan (DeepMind)
Mohammad Norouzi (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors