Prof. Dr.-Ing. Stefan Balke

Höxter, Germany

Trying to be a generalist with a deep understanding and intuition of recent technologies related to Data Engineer, Data Science, and Machine Learning. Currently leading a team of Data Scientists helping customers sorting their data, lifting its quality to ML-readiness, and eventually obtaining business value from modern data-driven approaches.

Before that, I obtained my PhD in applied Machine Learning research, namely Music Information Retrieval, supervised by Prof. Dr. Meinard Müller at the International Audio Laboratories Erlangen. I continued my research as a Post-Doc at the Institute for Computational Perception at JKU Linz, led by Prof. Dr. Gerhard Widmer. From 2019 to summer 2023, I led a team of data scientists at pmOne where we applied Machine Learning approaches to various industrial applications. Since fall 2023, I am professor for Data Science at Hochschule Weserbergland in Hameln.

A printable version of my curriculum vitae can be found here.

news

Aug 1, 2023	Happy to announce that I was appointed full professor for Data Science (W2) at Hochschule Weserbergland in Hameln.
May 25, 2023	Another (now almost yearly) funding by “Deutsche Gesellschaft für Engagement & Ehrenamt” for financing instruments. We will use these instruments to establish “Musikalische Früherziehung”, an offering to get kids from 4-6 used to concepts of pitch and rhythm through singing and musical instruments.
Feb 23, 2023	Wow, through local crowd funding, we were able to collect money to buy high-quality chimes for the orchestra. Might produce a dataset for that soon…

selected publications

MTD: A Multimodal Dataset of Musical Themes for MIR Research

Frank Zalkow, Stefan Balke, Vlora Arifi-Müller, and Meinard Müller

Transactions of the International Society for Music Information Retrieval (TISMIR), 3(1), 180–192, 2020

PDF Bib

@article{ZalkowBAM20_MTD_TISMIR,
  title = {{MTD}: {A} Multimodal Dataset of Musical Themes for {MIR} Research},
  author = {Zalkow, Frank and Balke, Stefan and Arifi-Müller, Vlora and Müller, Meinard},
  journal = {Transactions of the International Society for Music Information Retrieval ({TISMIR})},
  volume = {3},
  number = {1},
  year = {2020},
  pages = {180--192},
  doi = {10.5334/tismir.68},
  abbr = {TISMIR},
  selected = {true},
  pdf = {2020_ZalkowBAM_MTD_TISMIR.pdf}
}

Score Following as a Multi-Modal Reinforcement Learning Problem

Florian Henkel, Stefan Balke, Matthias Dorfer, and Gerhard Widmer

Transactions of the International Society for Music Information Retrieval (TISMIR), 2(1), 67–81, 2019

PDF Code Bib

@article{HenkelBDW19_ScoFoRL_TISMIR,
  author = {Henkel, Florian and Balke, Stefan and Dorfer, Matthias and Widmer, Gerhard},
  title = {Score Following as a Multi-Modal Reinforcement Learning Problem},
  journal = {Transactions of the International Society for Music Information Retrieval ({TISMIR})},
  volume = {2},
  number = {1},
  pages = {67--81},
  year = {2019},
  doi = {http://doi.org/10.5334/tismir.31},
  abbr = {TISMIR},
  selected = {true},
  pdf = {2019_HenkelBDW_ScoreFollowingRL_TISMIR.pdf},
  code = {https://github.com/CPJKU/score_following_game}
}

Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies

Meinard Müller, Andreas Arzt, Stefan Balke, Matthias Dorfer, and Gerhard Widmer

IEEE Signal Processing Magazine, 36(1), 52–62, 2019

PDF Bib

@article{MuellerABDW19_MusicRetrieval_IEEE-SPM,
  author = {M{\"u}ller, Meinard and Arzt, Andreas and Balke, Stefan and Dorfer, Matthias and Widmer, Gerhard},
  title = {Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies},
  journal = {{IEEE} Signal Processing Magazine},
  volume = {36},
  number = {1},
  pages = {52--62},
  year = {2019},
  url = {https://doi.org/10.1109/MSP.2018.2868887},
  doi = {10.1109/MSP.2018.2868887},
  pdf = {2019_MuellerABDW_MusicRetrieval_IEEE-SPM_arXiv.pdf},
  abbr = {IEEE-SPM},
  selected = {true}
}