Christian J. Steinmetz

ai-audio-startups. Community list of startups working with AI in audio and music technology

auraloss. Collection of audio-focused loss functions in PyTorch

pyloudnorm. Flexible audio loudness meter in Python with implementation of ITU-R BS.1770-4 loudness algorithm

dasp-pytorch. Differentiable audio signal processors in PyTorch

steerable-nafx. Steerable discovery of neural audio effects

micro-tcn. Efficient neural networks for analog audio effect modeling

ronn. Randomized overdrive neural networks

pymixconsole. Headless multitrack mixing console in Python

wavebeat. End-to-end beat and downbeat tracking in the time domain.

automix-toolkit. Models and datasets for training deep learning automatic mixing models

AutomaticMixingPapers. Important papers and associated code on automatic mixing research

IIRNet. Direct design of biquad filter cascades with deep learning by sampling random polynomials.

NeuralReverberator. Reverb synthesis via a spectral autoencoder

flowEQ. β-VAE for intelligent control of a five band parametric EQ

st-ito. Audio production style transfer with inference-time optimization

bela-zlc. Zero-latency convolution on Bela platform

neural-2a. Neural network model of the analog LA-2A dynamic range compressor

MixCNN. Convolutional Neural Network for multitrack mix leveling

pyloudnorm-eval. Evaluation of a number of loudness meter implementations

computational-music-creativity. Materials for the Computational Music Creativity course at UPF-MTG (Spring 2020)

findio. The Spotify search you don't need and never wanted

PhaseAnalyzer. C++ plugin built with the JUCE Framework to provide insight about the relative phase relationship of audio signals

Cinuosity. Novel playlist generation and music discovery in Spotify

OpenAudio. A list of open source VST/audio plugin projects. Please contribute more links or open source your own plugins.

mids. Implementation of content-based audio search algorithm.

auxCord. Sync Spotify accounts to build tailored playlists

DeepAFx-ST-dev. DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/

pyreqs. Easily build requirements.txt files automatically

youtube-audio-dl. Utility to automate download and normalization of YouTube audio streams

ddsp. DDSP: Differentiable Digital Signal Processing

tempnetic. Tempo estimation

amida. audio mixing interface for data acquisition

machine-learning. Materials for the Machine Learning course at UPF-MTG (Winter 2019)

consynthance. Studying consonance as a result of vocal similarity

ML4AP. Slides for my talk Applications of machine learning for assistive and creative audio plugins

Keras-GAN. Collection of accessible implementations of Generative Adversarial Networks in Keras.

LDA-Music. LDA topic modeling of raw audio data for music suggestions

arte. generative artwork created with canvas-sketch

cavae. Covert art variational autoencoder for generating new cover art

AudioTechTalks-S19. Materials and associated code for audio technology talks at Clemson University - Spring 2019

LoudnessHistory. An analysis of the perceived loudness of music over time.

aes-presenters-145th. Analysis of papers and presenters at the 145th AES Convention in NYC

sms-tools. Sound analysis/synthesis tools for music applications