Autoencoding Neural Networks as Musical Audio Synthesizers

04/27/2020
by   Joseph Colonel, et al.
1

A method for musical audio synthesis using autoencoding neural networks is proposed. The autoencoder is trained to compress and reconstruct magnitude short-time Fourier transform frames. The autoencoder produces a spectrogram by activating its smallest hidden layer, and a phase response is calculated using real-time phase gradient heap integration. Taking an inverse short-time Fourier transform produces the audio signal. Our algorithm is light-weight when compared to current state-of-the-art audio-producing machine learning algorithms. We outline our design process, produce metrics, and detail an open-source Python implementation of our model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/04/2021

Network Modulation Synthesis: New Algorithms for Generating Musical Audio Using Autoencoder Networks

A new framework is presented for generating musical audio using autoenco...
research
02/15/2022

Phase Vocoder Done Right

The phase vocoder (PV) is a widely spread technique for processing audio...
research
04/28/2019

Application of Autoencoder-Assisted Recurrent Neural Networks to Prevent Cases of Sudden Infant Death Syndrome

This project develops and trains a Recurrent Neural Network (RNN) that m...
research
08/26/2020

TIV.lib: an open-source library for the tonal description of musical audio

In this paper, we present TIV.lib, an open-source library for the conten...
research
10/25/2019

Learning audio representations via phase prediction

We learn audio representations by solving a novel self-supervised learni...
research
09/16/2021

Graph Fourier Transform based Audio Zero-watermarking

The frequent exchange of multimedia information in the present era proje...

Please sign up or login with your details

Forgot password? Click here to reset