Resources

Downloadable Data, Code, and Software

We offer data and executable code to help and inspire researchers, students, or anybody interested in our research topics.

  • trackswitch.js: A versatile web-based audio player for presenting scientific results.
  • webMUSHRA: Tool to carry out MUSHRA experiments within the web browser while at the same time being compliant to the ITU-R Recommendation BS.1534 (MUSHRA).
  • Signal Separation Evaluation Campaign (SiSEC 2016): Introduction to state-of-the-art algorithms in audio source separation for the demixing of professionally produced music.
  • The Adjustment/Satisfaction Test (A/ST): A perceptual test where subjects interact with a user-adjustable system. Their adjustment preferences and the resulting satisfaction levels are studied.
  • Vandermonde Tools: Implementations of the most central functions required for using the Vandermonde transform, including Vandermonde factorization of symmetric Toeplitz matrices.
  • Subjective Evaluation of Blind Audio Source Separation Database (SEBASS-DB): A collection of subjective ratings on the perceived quality of separated audio source signals.
  • torch-pesq: PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio.

You can find more topic-specific software and datasets at the following locations:

Demos

Demonstrations of our technologies and research results are available as music or video playback within the following research fields:

Tutorial Content