392137 Auditory Data Science (V) (SoSe 2024)

The lecture introduces the research field of Auditory Data Science which aims at using sound as medium for exploratory data analysis of complex data, for monitoring changes in complex data streams, for discriminating complex time series that are difficult to understand from visualization alone, for supporting exploratory interactions with complex data, to enhance our insight into data by teaming up visualization and sonification towards multimodal data exploration.
Sonification, the systematic, reproducible representation of data as sound is the key to auditory data science and thus sonification techniques will be at the core of this lecture. However, auditory data science has to also focus on established practises for data exploration, involve a basic set of methods for inductive data mining, e.g. for topology learning, intrinsic dimensionality estimation, clustering, covariance estimation. In this lecture we will learn all required techniques, from data mining and sonification to interactive interfaces to realize systems for modern data exploration. A number of real-world examples for auditory data analysis including but not limited to exploration of medical data will be presented and discussed in the lecture. Participants will be capable to use, understand and develop modern sonification systems for understanding structure in high-dimensional data, and be able to craft sound synthesizers and dynamic models for real-time sonification rendering.

Requirements for participation, required level

The lecture is for anybody interested in scientific applications of auditory display. Helpful, but not mandatory lectures are Sonification & Sound Synthesis, Introduction to Data Mining.

Bibliography

Hermann, Hunt, Neuhoff (Eds.). The Sonification Handbook, Logos Verlag, Berlin, 2011, online at sonification.de/handbook