Loss Functions in Audio ML
An informal survey of objective functions used in Machine Learning in the audio domain.
Generating music in the waveform domain
benanne.github.ioThis is a write-up of a presentation on generating music in the waveform domain, which was part of a tutorial that I co-presented at ISMIR 2019 earlier this month.
Diffusion models are autoencoders
Diffusion models have become very popular over the last two years. There is an underappreciated link between diffusion models and autoencoders.
Musings on typicality
A summary of my current thoughts on typicality, and its relevance to likelihood-based generative models.
wav-nn: Generating wav files with a neural network
This post is about a project to generate wav files with a neural network. These are files with the audio in the waveform domain, i.e. as sound samples such as that which might be converted to mp3 files.