Apply neural networks to Virtual Analog modeling of audio effects.

Listen on:

All podcast episodes.

Sign up for WolfSound’s newsletter!

In this podcast episode, I was lucky to interview another member of the Aalto Acoustics Lab of the Aalto University in Espoo, Finland. He is involved in research applying deep learning to audio, for example, in the context of Virtual Analog modeling of guitar amplifiers. He was also the advisor of my Master Thesis.

Note: if you like the podcast so far, please, go to iTunes and leave me a review there. It will benefit both sides: more reviews means more outreach on iTunes and feedback can help me to improve the show and provide better quality content to you. Thank you for doing this.

Episode Contents

In this podcast episode, you will learn

  • how to transition from mechanical engineering to audio processing,
  • how to apply deep learning to music processing, for example, virtual analog modeling,
  • challenges of deep learning in audio,
  • how to use neural networks in real-time audio,
  • what makes a good audio dataset,
  • how to fuse traditional DSP and deep learning,
  • typical neural network architectures in audio,
  • generative models in audio,
  • how transition from the Master’s to the PhD mindset,
  • challenges of remote research collaboration during pandemic,
  • transition from Scotland to Finland.

Referenced Resources

Below are all the resources that are referenced in the podcast episode.

Thank you for listening! Please, consider rating the podcast on iTunes!