This information is about a former employee. It may be outdated.

Dr.-Ing. Yigitcan Özer

Research Interests

  • Audio Source Separation
  • Music Synchronization
  • Audio Decomposition & Reconstruction
  • Text-to-Speech Synthesis

CV

  • 09/2024 – 12/2024: Rearch Intern at Sony AI, Tokyo
  • 01/2021 – 08/2024: PhD Student at the International Audio Laboratories Erlangen
    • PhD thesis: Source Separation of Piano Music Recordings
  • 01/2019 – 12/2020: Research Associate at Spoken Language Processing Group, Fraunhofer IIS, Erlangen
  • 07/2017 – 12/2018: Data Science Consultant at Data Insights GmbH, Munich
  • 01/2016 – 06/2017: Machine Learning Engineer at Cape Analytics GmbH, Munich
  • 09/2013 – 11/2015: MSc in Communications Engineering, TU Munich
    • Master's thesis: Multimodal Deep Convolutional Neural Network for Surface Classification
  • 09/2009 – 06/2013: BSc in Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey

Teaching

Former and Current Students

  • Jeet Sen Sarma: HiWi
  • Abhirup Saha: HiWi
  • Fatemeh Eftekhar: HiWi
  • Maryam Pirmoradi: HiWi
  • Moumita Chakraborty: Research Internship
  • Daniel Scheller: HiWi
  • Jeremy Lawrence: HiWi
  • Yunbei Huang: Research Internship, Master Thesis
  • Leo Brütting: HiWi, Master Thesis
  • Jonathan Hansen: Research Internship, Master Thesis
  • Edgar Andrés Suárez Guarnizo: Master Thesis

Scientific Activities & Workshops

Peer-Reviewing

  • IEEE Open Journal of Signal Processing
  • IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Transactions of the International Society for Music Information Retrieval (TISMIR)
  • International Society for Music Information Retrieval Conference (ISMIR)
  • Journal of Open Source Software (JOSS)