Robin Scheibler

esp32-fft. Vanilla single-precision radix-2 FFT for the ESP32.

fast_bss_eval. A fast implementation of bss_eval metrics for blind source separation

diffusion-separation. Single channel speech source separation by diffusion process (ICASSP 2023)

torchiva. Blind source separation with independent vector analysis family of algorithm in torch

auxiva-ipa. Fast algorithm for determined blind source separation with update of demixing filters with joint adjustment of the remaining sources.

CmdArduino. Simple serial command line prompt for Arduino. Developed by Akiba from @freaklabs

Pomodoro. A custom built timer for the pomodoro technique to be more productive.

piva. Performance-oriented implementation of independent vector analysis for blind source separation.

2020_interspeech_gmdp. Generalized Minimal Distortion Principle for Blind Source Separation

pyramic-dataset. 48-Channel Anechoic Audio Recordings of 3D Sources

doamm. Implementation of algorithms for refinement of direction of arrival estimators by optimization

create_wsj1_2345_db. Collection of scripts to create a dataset of noisy multi-channel reverberant mixtures based on wsj1 and CHiME3 datasets.

mighty-1284p. Mighty 1284P Platform for Arduino

separake. Echo aware source separation

interspeech2023-moving-iva-samples. Repository containing samples produced by the method proposed in "Multi-channel separation of dynamic speech and sound events" and presented at Interspeech 2023.

auxiva-iss-dnn. Code to reproduce the results in the paper "Surrogate Source Model Learning for Determined Source Separation"

pyramic-demo. A few routines for audio processing (real-time).

room-impulse-responses. A list of publicly available room impulse response datasets and scripts to download them.

cookiecutter-pyroomacoustics-sim. A cookie cutter to quickly get started with room simulation using pyroomacoustics.

bss_speech_dataset. A dataset to test blind source separation algorithms

AudioTools. Audio signal processing toolbox in python.

sdr_medium_rare. Code to reproduce results in the paper "SDR - Medium Rare with Fast Computations"

lps. Levenshtein Phoneme Similarity (forked from https://git.rz.tu-bs.de/ifn-public/LPS)

jisamm. Code the paper on MM algorithms for joint independent subspace analysis

maxsinr-raking-echoes. Is the MaxSINR beamformer raking echoes?

python-samplerate2. Monolithic python wrapper of libsamplerate

timeseries-api. A dead simple API to store measurements taken with IoT devices such as ESP8266 or ESP32.

nerdledger. CLI family accounting sw in Python

kurodako. A beaglebone black cape with 8 microphone arrays, as many as an octopus has legs.

moteur. Sketch of a physics engine coded as an exercise back around 2004.

bsseval. audio source separation evaluation metrics

beamerthemelausanne. A beamer theme with full screen background images for main and section titles.

SpectroDiversity. This is a simple real-time audio spectrum analyzer written in processing during #HLab2014 in Yoygyakarta, Indonesia.

wignerpy. A python library to compute the Wigner 3j and 6j symbols with very large l values. All the calculation is carried out in C++. Under the hood C++ code made by Joey Dumont (github user valandil).

Breathalyzer. Evolution from a badge hacking contest at Hashdays 2012.

graphcoloring_mcmc. Implementation of simulated annealing for the graph coloring problem.