Department of Computational Perception
Department of
Computational Perception
Johannes Kepler Universitšt Linz

Home  –  Mission  –  Teaching  –  People  –  Research  –  Media  –  Awards  –  Impressum


<< back to Music Understanding & Tracking

One active research field at our institute is the automatic estimation of beat and downbeat (beginning of a bar) times from an audio signal. While these systems work mostly well in offline scenarios (where the system has access to the whole audio signal), they often fail in cases where this information is not available (online mode). This online beat/downbeat tracking is particularly important for interactive music systems, e.g. robots that play music with human musicians.

Drum-O-Tron 3000

Recently, our institute constructed a working prototype of a drum "robot", that is able to accompany a musician by "listening" to what he/she is playing, detecting the rhythmic structure, and playing accordingly. However, it is limited in what it can do:

  • It can only detect a small number of rhythms.
  • It does not handle rhythm variations very well.
  • For each of these rhythms, it can only play a predefined drum pattern.
  • Learning new rhythms is a manual, tedious task.

This context opens the possibility to work on multitude of topics. These topics range from practical implementations of algorithms with real-time constraints, to applied (offline) machine learning.

Note that musical knowledge is not strictly necessary to work on any of these topics.

Open Topics:

  • Finding Suitable Drum Patterns for Given Rhythmic Inputs
    without the need to manually specify drum patterns for each learned rhythm. Here, we assume that we have a database of drum rhythms to choose from.
  • Generating Drum Patterns (Fitting Certain Styles or Rhythms).
    The goal is to create a generative model that is able to create new, good sounding drum rhythms on demand.
  • Interactive Ad-hoc Learning of New Rhythms.
    Simplify the task of "teaching" Drum-O-Tron new rhythms by leveraging the power of transfer learning methods. The goal is to enable the user to conveniently teach the computer a new rhythm giving only few examples.
  • Real-time Downbeat Tracking Robust to Rhythmic Variations.
    Make Drum-O-Tron less sensitive to rhythmic variations by either inventing a new real-time downbeat tracker or combining existing approaches available at our institute.
  • Automatic Drumstick Delay Calibration.
    Before using Drum-O-Tron, it is necessary to configure the delay compensation for each stick individually so Drum-O-Tron can play in time. Implement and test a method that automatically determines the delay and configures Drum-O-Tron accordingly.

Contact: Florian Krebs, Filip Korzeniowski

The Automatic Ballroom Dance Instructor

Imagine you are on a wedding and the band starts to play. Everybody gets up, finds a partner and starts to dance. You always thought that ballroom dances are boring, but somehow the bands plays really great and you are getting bored sitting alone in the corner. You switch on the Automatic Ballroom Dance Instructor (ABDI) app on your smartphone, let the app listen to 20 seconds of a song and it immediatly tells you which dance style you should dance. Moreover, it also displays a sequence of dance steps synchronised to the music, making it easy for you to follow, join the crowd and dance through the night...

In this context, the following topics could be considered:

Contact: Florian Krebs

last edited by kf on Sep 29, 2015