This page gives a short description of the projects I developed or am involved in on GitHub.
rtHMM is a C++ library implementing the major inference algorithms for Hidden Markov Models. I designed it with a focus on real-time data processing. It thus efficiently handles large state spaces, especially if they are sparse. I developed it at the beginning of my PhD studies for a HMM-based score following system. I don’t actively work on it anymore, but the current version is quite usable. For example, rtHMM powers the mighty Drum-O-Tron 3000, a live drum accompaniment “robot” created at the Department of Computational Perception:
I contribute to madmom, an audio processing library written in Python by Sebastian Böck at the Department of Computational Perception. It facilitates prototyping audio processing systems and converting them to “picklable” processing modules. Madmom contains processing modules of state-of-the-art algorithms for onset, beat, and downbeat detection, as well as tempo estimation.