Welcome to my personal website!

I’m Yigitcan Özer, a postdoctoral researcher at the Yamagishi Lab, National Institute of Informatics in Tokyo, Japan. I specialize in audio processing, with a focus on watermarking and generative models for speech and music.

After earning my B.Sc. from Bilkent University (Turkey) and M.Sc. from the Technical University of Munich (Germany), I completed my Ph.D. at the International Audio Laboratories Erlangen under the supervision of Prof. Meinard Müller. Before that, I worked at Fraunhofer IIS as a research associate in the Spoken Language Processing Group.

🎶 Merging Music and Research

During my Ph.D., I pursued a project deeply connected to my identity as a pianist. I’ve always dreamed of playing a piano concerto with an orchestra — but instead of waiting for that opportunity, I decided to create it myself. This led to my work on source separation of piano concertos, enabling me to extract orchestral parts from recordings and play alongside them. This journey resulted in a personally meaningful integration of science and art. One highlight was performing with Mozart’s Piano Concerto in D minor using a custom orchestral backing generated as a final product of my Ph.D. You can explore the project and listen to further audio demos here.

💻 Industry Meets Academia

Before returning to research, I spent three years in industry. At an American startup in Munich, I worked on deep learning for computer vision, and later became an IT consultant, developing solutions in Python and C++ across various domains. In 2019, I rejoined academia through a research position at Fraunhofer IIS, contributing to text-to-speech synthesis.

🧠 Side Passions

I’m a self-declared language nerd who enjoys diving into etymology and steadily learning new languages. During my Ph.D., I also co-led workshops on electronic instrument design for high school students at Fraunhofer IDMT in Ilmenau — blending outreach, music, and engineering.

If you’re a fellow researcher, musician, language geek, or just a curious mind — I’d love to connect. Cheers!