Fabian Ostermann

• AI Computer Music and Algorithmic Composition
• Human-centered AI
• (Generative) Reinforcement Learning
• Evolutionary Algorithms (Neuroevolution)
• Procedural Content Generation (for Games)

Courses

• WS25/26 Vorlesungseinheiten in der Ringvorlesung Musikdatenanalyse zum Thema Automatische Komposition
• WS25/26 Fachprojekt Digital Entertainment Technologies
• SS25 Übung zur Vorlesung Praktische Optimierung
• WS24/25 Fachprojekt Musikinformatik
• SS24 Fachprojekt Musikinformatik
• WS23/24 Fachprojekt Digital Entertainment Technologies
• SS23 Übung zur Vorlesung Praktische Optimierung
• WS22/23 Vorlesungseinheit in der Ringvorlesung Musikdatenanalyse zum Thema Automatische Komposition (Folien)
• WS22/23 Fachprojekt Digital Entertainment Technologies
• SS22 Fachprojekt Digital Entertainment Technologies
• WS21/22 Praktikum zur Vorlesung Einführung in die Progammierung
• WS20/21 Übungseinheiten in der Ringvorlesung Musikdatenanalyse
• SS2017 Übungseinheiten in der Ringvorlesung Musikdatenanalyse

Supervised Theses

• Development of an adaptive music system for a word game
• Koordination multipler Agenten in einem Stealth-Videospiel mit einer Blackboard-Architektur
• Evolutionsbasierte Musikgenerierung mit interaktiven und regelbasierten Fitnessfunktionen
• Using Neuroevolution for Training a Pokemon Red Agent
• Vergleich von internen und externen Zuständen als Eingabe in ein adaptives Musiksystem für Videospiele
• Generierung von Jazz-Soli mit Diffusionsmodellen
• Efficient Physics Models of Super Mario Odyssey for Accelerated Agent Training
• Textbasierte evolutionäre Musikgenerierung mit vortrainierten Sprachmodellen als Fitnessfunktion
• Grafische Darstellung hochdimensionaler Fuzzy Cluster durch Projektion und Alpha-Schnitte
• Hyperparameteroptimierung eines neuroevolutiven Ansatzes für ein Autorennspiel
• An Evolutionary Approach to Recreating Vector Graphics from Raster Graphics
• Einsatz von Adversarial Reinforcement Learning zur automatischen Erstellung spielbarer Level in einem einfachen Rennspiel
• Transformer based drum track generation for electronic dance music
• Generierung von Orchesterstücken mit Transformer-Modellen

Articles (peer reviewed)

• Using Large Language Models as Fitness Functions in Evolutionary Algorithms for Music Generation (PDF,CODE)
  Fabian Ostermann, Jonas Kramer, Günter Rudolph
  Proceedings of the Conference on AI Music Creativity (AIMC), 2025

• Emergency Corridor Building on Multi-Lane Motorways with Autonomous Model Cars (VIDEO)
  Jurij Kuzmic, Günter Rudolph, Fabian Ostermann
  International Conference on Internet of Things, Big Data and Security (IoTBDS), SciTePress, 2024, pp. 321–328.

• Adaptation and Optimization of AugmentedNet for Roman Numeral Analysis Applied to Audio Signals (PDF)
  Leonard Fricke, Mark Gotham, Fabian Ostermann, Igor Vatolkin
  International Conference on Evolutionary and Biologically Inspired Music and Art (EvoMUSART), Springer, 2024, pp. 146–161.

• 🏆 Adaptive video game music as a multi-objective benchmark for conditional autoregressive models (PDF)
  Fabian Ostermann
  Proceedings 33rd Workshop Computational Intelligence, KIT Scientific Publishing, 2023, pp. 199–214
  

• Application of Neural Architecture Search to Instrument Recognition in Polyphonic Audio (PDF)
  Leonard Fricke, Igor Vatolkin, Fabian Ostermann
  International Conference on Evolutionary and Biologically Inspired Music and Art (EvoMUSART), Springer, 2023, pp. 117–131

• Musical Genre Recognition based on Deep Descriptors of Harmony, Instrumentation, and Segments (PDF)
  Igor Vatolkin, Mark Gotham, Néstor Nápoles López, Fabian Ostermann
  International Conference on Evolutionary and Biologically Inspired Music and Art (EvoMUSART), Springer, 2023, pp. 413–427

• AAM: A Dataset of Artificial Audio Multitracks for Diverse Music Information Retrieval Tasks (PDF,DATASET,CODE)
  Fabian Ostermann, Igor Vatolkin, Martin Ebeling
  EURASIP Journal on Audio, Speech, and Music Processing (2023)

• Artificial Music Producer: Filtering Music Compositions by Artificial Taste (PDF, VIDEO)
  Fabian Ostermann, Igor Vatolkin, Günter Rudolph
  Proceedings of the Conference on AI Music Creativity (AIMC), 2022

• Evaluating creativity in automatic reactive accompaniment of jazz improvisation (PDF)
  Fabian Ostermann, Igor Vatolkin, Günter Rudolph
  Transactions of the International Society for Music Information Retrieval (TISMIR) 4 (2021), Nr. 1

• An evolutionary multi-objective feature selection approach for detecting music segment boundaries of specific types (PDF)
  Igor Vatolkin, Fabian Ostermann, Meinard Müller
  Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2021, pp. 1061–1069

• Evaluation rules for evolutionary generation of drum patterns in jazz solos (PDF,VIDEO,CODE)
  Fabian Ostermann, Igor Vatolkin, Günter Rudolph
  International Conference on Evolutionary and Biologically Inspired Music and Art (EvoMUSART), Springer, 2017, pp. 246–261

Theses

• Modellierung des menschlichen Musikgeschmacks mit neuronalen Netzen
  Fabian Ostermann, Master-Thesis, TU Dortmund, 2021

• Ortung einer akustischen Quelle im Roboterfußball mittels Multilateration
  Fabian Ostermann, Studienarbeit, TU Dortmund, 2020

• Erzeugung perkussiver Muster zur Echtzeitbegleitung von Jazz-Soli
  Fabian Ostermann, Bachelor-Thesis, TU Dortmund, 2015

• Held Horizon: AI–human co-creation experiment on composing for choir
  The music piece “Held Horizon” is the result of an AI–human co-creation experiment I performed using ChatGPT 5. It was selected for the workshop Choir in the Loop: Singer-Aware AI Composition Practice, which is part of the Conference on AI Music Creativity 2025.

• Dataset of Artificial Audio Multitracks (AAM)
  The dataset contains 3,000 artificial music audio tracks with rich annotations. It is based on real instrument samples and generated by algorithmic composition with respect to music theory.

• ArtificialSongGenerator (Github)
  Algorithmic music composition tool used to compile the AAM dataset.

• EAR Drummer (Github) (YouTube demo, more audio demos)
  EAR Drummer is a interactive music system that generates rhythmical drum patterns and bass lines. It produces midi output that provides backing music to accompany a Jazz soloist in realtime. It uses Evolutionary Computing, is fully Autonomous and Reacts to midi input.

• EvoMUSART, Part of Evo* (PC Member 2024, 2025, 2026)
• IJCAI (PC Member, Special Track on AI, the Arts, & Creativity)

• Computer Music Journal
• Journal of New Music Research
• Transactions of the Intl. Society for Music Information Retrieval