Teaching

Open, Creative-Commons-licensed teaching materials (lectures, seminars, and Jupyter notebooks) are available at machinelistening.github.io.

Selected Lectures (University of Bamberg)

• Computational Analysis of Sounds and Music (CH-CASM-M) (Winter semester)
  Deep learning and audio signal processing fundamentals with applications in music information retrieval (transcription, source separation, harmonic analysis) and environmental acoustics (sound event detection, scene classification, anomaly detection), implemented in Python using deep learning frameworks.
  Course Description · Jupyter Notebooks (Seminar).
• Introduction to Audio and Music Processing (CH-EAM-B) (Summer semester)
  Foundations of audio signal processing and acoustics with applications in music information retrieval, including structure analysis, music synchronization, recognition tasks (tempo, beat, chord, pitch), source separation, and machine learning-based audio classification.
  Course Description · Jupyter Notebooks (Seminar).

Past Lectures

• Computational Analysis of Sounds and Music (CASM) (2024, lecture + seminar, TU Ilmenau)
  Foundations of audio signal processing, machine learning, and deep learning, with applications in music information retrieval and environmental sound analysis, plus a hands-on Python research project.
• KI-gestützte Audioanalyse von Musik und Soundscapes (2023/2024, research seminar, HfM Weimar / Institut für Musikwissenschaft Weimar-Jena, with Prof. Martin Pfleiderer)
  Deep learning for humanities research questions in audio and music. Student evaluation: 4.5/5.
• Machine Listening for Music and Sound Analysis (2014–2024, TU Ilmenau; also AIDA Doctoral Academy)
  Self-contained units within the “Audio Systems Technology” lecture (Prof. Dr.-Ing. Dr. rer. nat. h.c. mult. Karlheinz Brandenburg).
• Environmental Sound Analysis (guest lectures, TH Nürnberg & FAU Erlangen-Nürnberg)
  Acoustic scene analysis, sound event detection, and acoustic anomaly detection.