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

From statwiki
Jump to: navigation, search
(Created page with "= Introduction = = Contributions = = Models = center == WaveNet Autoencoder == Mu-law encoding: == Baseline: Spectral Autoencoder...")
 
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

paper26-figure1-models.png

WaveNet Autoencoder

Mu-law encoding:


Baseline: Spectral Autoencoder

Training

The NSynth Dataset

Evaluation

Reconstruction

paper27-figure2-reconstruction.png
paper27-table1.png

Interpolation in Timbre and Dynamics

paper27-figure3-interpolation.png

Entanglement of Pitch and Timbre

paper27-figure4-entanglement.png
paper27-table2.png

Future Directions

References