Neural Audio Synthesis of Musical Notes with WaveNet autoencoders: Difference between revisions

From statwiki
Jump to navigation Jump to search
(Created page with "= Introduction = = Contributions = = Models = center == WaveNet Autoencoder == Mu-law encoding: == Baseline: Spectral Autoencoder...")
 
No edit summary
Line 26: Line 26:
[[File:paper27-figure2-reconstruction.png|center]]
[[File:paper27-figure2-reconstruction.png|center]]


[[Media:Flugelhorn-Original.ogg|left]]
[[File:paper27-table1.png|center]]


== Interpolation in Timbre and Dynamics ==
== Interpolation in Timbre and Dynamics ==
Line 35: Line 35:


[[File:paper27-figure4-entanglement.png|center]]
[[File:paper27-figure4-entanglement.png|center]]
[[File:paper27-table2.png|center]]


= Future Directions =
= Future Directions =
= References =

Revision as of 08:52, 22 March 2018

Introduction

Contributions

Models

WaveNet Autoencoder

Mu-law encoding:


Baseline: Spectral Autoencoder

Training

The NSynth Dataset

Evaluation

Reconstruction

Interpolation in Timbre and Dynamics

Entanglement of Pitch and Timbre

Future Directions

References