392268 ISY Project: Listen to your Data - Sonification for Auditory Data Science (Pj) (SoSe 2019)

Sonification is the auditory representation of data as sound, for the purpose of discovering and understanding hidden patterns and regularities. So far, most sonifications are individually designed and specially crafted for a given application and researchers lack a toolbox for sonification that they can use will little configuration yet nonetheless high flexibility for any given dataset. The goal of this project is to continue on a given basic python package to enhance it to be easily usable for the standard sonification types, including audification, parameter-mapping sonification, model-based sonification and wave-space sonification. Python (numpy/scipy) is used for data processing and visualization, and SuperCollider and pyaudio and/or pyo for the audio rendering. Matplotlib and other estabished visualization front-ends shall be integrated so that sonifications can be excited seamlessly by clicking in scatter plots. Interactive interfaces will be developed for selected sonification approaches so that users can control the relevant parameters interactively. Many code pieces are available, so depending on preference, participants can integrate, or rewrite methods.
A collection of benchmark data sets including medical data (ECG, EEG), image data and non-time-indexed data will be provided to test, demonstrate and verify the sonification tools.

Please note that the teams will be selected by the supervisors on the basis of short applications that students are expected to send to them. Registering to the project in the ekVV will only be regarded as expression of interest; it will not secure a team membership. Please get in touch with the supervisors for information on the application procedure.

Teilnahmevoraussetzungen, notwendige Vorkenntnisse

Required skills

• good knowledge in Python 3.x
• basic knowledge in audio signal processing is beneficial
• basic knowledge in machine learning, data mining or visualization