Supervision

NOTE: Due to a high number of teaching responsibilities in 2026SS (One 4 SWS lab course, two or maybe three Master’s thesis projects), I will not be able to supervise new students. Thank you for your understanding.

Thesis Topics

I supervise the following topics:

1. Audio Deepfake Detection: Model training and analysis; requires familiarity with our codebase IMS-ADD.
2. Codec-based Speech Synthesis: Prompting and fine-tuning TTS or ALM models; audio reconstruction using neural audio codecs.
3. Speech Analysis: Analyzing speech to better understand speech models. Example tools include librosa, openSMILE, Parselmouth, speechmetrics, and SpeechBrain. Relevant models can sometimes be found on HuggingFace, e.g., speech enhancement models.

Availability

My schedule will be very tight from September 2025 to March 2026. During this period, I won’t be able to provide close, hands-on supervision. But new thesis projects are possible under the following conditions:

1. You are confident that the project will not be overly challenging for you, so you only need high-level guidance.
2. You are preparing an industry paper with a supervisor from the company, and mainly need support from me with the writing process.

In short, I will likely not have the time to provide detailed help. I encourage you to select a topic that aligns with your strengths. Please DO NOT choose a challenging topic and assume AI tools can solve these issues! Based on past experience, AI (chatbots or editors) often suggests quick fixes to the codebase. Once these pile up, the project becomes messy and ugly and unmanagable, so everyone suffers.

If you would like to do a thesis with me, to help me assess whether a topic might be too challenging, please contact me with your topic preference and a self introduction (e.g., your background, CV, etc.).