Dr. Sören Schulze

Research Areas

• Audio and signal processing
• Blind source separation
• Time-frequency representations
• Machine Learning

Theses (Selection)complete list

1. Klaviertonhöhenerkennung mit Convolutional Neural Networks (Pegah Golchian)

Publications (Selection)complete list

1. S. Schulze.
   Blind source separation in single-channel polyphonic music recordings.
   Dissertationsschrift, Universität Bremen, 2022.

   online at: https://media.suub.uni-bremen.de/handle/elib/5816

2. S. Schulze, E. King.
   Formulating Beurling LASSO for Source Separation via Proximal Gradient Iteration.
   Zur Veröffentlichung eingereicht.

   online at: https://doi.org/10.48550/arXiv.2202.08082

3. S. Schulze, E. King.
   Sparse Pursuit and Dictionary Learning for Blind Source Separation in Polyphonic Music Recordings.
   EURASIP Journal on Audio, Speech, and Music Processing, 6:2-25, 2021.

   DOI: 10.1186/s13636-020-00190-4
   online at: https://rdcu.be/ceo1J

4. S. Schulze, J. Leuschner, E. King.
   Blind Source Separation in Polyphonic Music Recordings Using Deep Neural Networks Trained via Policy Gradients.
   MDPI Open Access Journals Signals, 2(4):637-661, 2021.

   DOI: 10.3390/signals2040039
   online at: https://www.mdpi.com/2624-6120/2/4/39

5. S. Schulze, E. King.
   A Frequency‐Uniform and Pitch‐Invariant Time‐Frequency Representation.
   90th GAMM Annual Meeting of the international Association of Applied Mathematics and Mechanics (GAMM), 18.02.-22.02.2019, Vienna, Austria.
   Proc. Appl. Math. Mech., 19(1):e201900374, 2019.

   DOI: 10.1002/pamm.201900374