With the creation of large audio collections, it is necessary to devise ways to make those collections accessible to the users. Currently, access to music repositories is mostly limited to query-based retrieval based on textual  meta-data, with some advanced systems supporting acoustic queries. What  Andreas Rauber and Thomas Lidy would like to have additionally, is a way to  facilitate exploration of musical libraries. They thus need to automatically  organize music according to its sound characteristics in such a way that they  find similar pieces of music grouped together, allowing them to find a classical  section, or a hard-rock section etc. in a music repository.

Professor Rauber and Thomas Lidy research various methods of indexing and structuring audio collections, as well as providing intuitive user interfaces for a wide range of devices. Feature extraction from audio signals, incorporating  psychoacoustic information, is combined with textual features. Machine learning  techniques are used to extract semantic information, group audio by similarity,  or classify it into various genres. Advanced visualization techniques are  employed to provide intuitive interfaces to audio collections on standard PC as  well as mobile devices.

Audio Feature Extraction
Using methods from digital signal processing and psycho-acoustics the two computer scientists are extracting semantic information from music. The features extracted from the audio signal are able to describe the stylistic content of the  music, e.g. beat, presence of voice, timbre, etc. Thus, a system using audio feature extraction is able to tell about the content of a piece of music without the need of annotated labels such as artist, song title or genre. Moreover, it is able to find similar music automatically. Different kinds of feature sets (Rhythm  Patterns, amongst others) are the basis to many subsequent tasks, such as  automatic music organization or classification into genres.