course: Musikdatenanalyse

number:
140009
teaching methods:
lecture with tutorials
responsible person:
Prof. Dr.-Ing. Rainer Martin
lecturer:
Prof. Dr. Claus Weihs (extern)
language:
german
HWS:
3
CP:
see examination rules
offered in:
summer term

dates in summer term

  • start:

Exam

All statements pertaining to examination modalities (for the summer/winter term of 2020) are given with reservations. Changes due to new requirements from the university will be announced as soon as possible.

Date according to prior agreement with lecturer.

Form of exam:None
Registration for exam:None
Duration:30min
description of exam:

Die Prüfungsform wird zu Beginn der Veranstaltung bekanntgegeben.

goals

This course conveys the fundamentals of the analysis of music signals and music data. The participants acquire the methods of signal processing, statistics and classification in the context of music data.

content

The course is offered jointly by several faculties, namely the Faculty of Arts and Sports Sciences (Department of Music and Musicology) and the Faculty of Statistics of the TU Dortmund and the Faculty of Electrical Engineering and Information Technology of the Ruhr University Bochum.

Table of contents (lecturer in parentheses)

  1. Introduction, the music signal I (Weihs, Ebeling)
  2. The music signal II; musical structures (Ebeling)
  3. Digital signal processing I (Martin)
  4. Digital signal processing II, signal based features (Martin, Nagathil)
  5. Digital representation of music, non-signal based features (Rudolph, Vatolkin)
  6. Statistics of musical data (Weihs)
  7. Unsupervised learning (Weihs)
  8. Supervised classification (Weihs)
  9. Feature processing and feature selection (Vatolkin)
  10. Segmentation and transcription (Ligges)
  11. Instrument recognition (Weihs, Bauer)
  12. Review, amendments, Conclusion (Weihs, Bauer)

requirements

keine

recommended knowledge

Knowledge of higher mathematics, in particular fundamentals of probability and statistics and linear algebra.

miscellaneous

Die Vorlesung findet in der TU Dortmund im Raum OH 12 / 1.056 statt.

Die Teilnehmerzahl ist auf max. 30 begrenzt. Eine Anmeldung ist per E-mail bei Sabine Bell

sabine.bell@tu-dortmund.de

erforderlich.