Skip to content

Latest commit

 

History

History
40 lines (28 loc) · 1.76 KB

README.md

File metadata and controls

40 lines (28 loc) · 1.76 KB
Raw

Radetzky

Add randomised and volume-sensitive claps to detected beats on any audio file!

Demo here:

Video

Motivation

2021's Vienna New Year's Concert was the very first ran without an audience.

The Radetzky March is a staple every year--usually it is the last encore piece played, with the audience clapping along.

Riccardo Muti, the conductor of the 2021 edition, mentioned that "This is the first time the audience can listen to the March without the clapping". I thought it was weird, and hence this project was born.

Try it out!

Requirements

  • Python 3
  • Dependencies: 
    pip install -r requirements.txt

Running

  • Place source audio (only 44.1kHz files supported as of now) in data/.
  • Tweak the Parameters section in main.py.
  • Run the code! 
    python main.py
  • Output is in output/ with the same file name as the source's.

Acknowledgements

  • Clapping sound effect: see its README for attribution
  • Beat tracker (madmom):
    • Sebastian Böck, Florian Krebs and Gerhard Widmer, “A Multi-Model Approach to Beat Tracking Considering Heterogeneous Music Styles”, Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR), 2014.
    • Florian Krebs, Sebastian Böck and Gerhard Widmer, “An Efficient State Space Model for Joint Tempo and Meter Tracking”, Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR), 2015.