Stop using Image Interpolation for Neural Audio Synthesis

By Medium - 2021-03-15

Description

In this story I want to advance your current understanding of neural upsamplers in the context of audio synthesis. And provide a simple Subpixel1D Keras layer implementation to use as a drop-in…

Summary

  • The different types of Neural Upsamplers and which one you should use in your Deep Learning Audio Synthesis Project.
  • In the following sections we will have a closer look into the implementation of a Subpixel1D layer but let us first talk about the pro’s and con’s of the three methods so far.
  • Now let us put this layer into action by implementing a simple auto-encoder for raw audio data.

 

Topics

  1. Machine_Learning (0.41)
  2. Backend (0.19)
  3. NLP (0.13)

Similar Articles

ResNets — Residual Blocks & Deep Residual Learning

By Medium - 2020-12-02

Deep Learning harnesses the power of Big Data by building deep neural architectures that try to approximate a function f(x) that can map an input, x to its corresponding label, y. The Universal…

pytorch-widedeep: deep learning for tabular data

By Medium - 2021-02-22

This is the third of a series of posts introducing pytorch-widedeepa flexible package to combine tabular data with text and images (that could also be used for “standard” tabular data alone). The…