Master Theses
For general information regarding student theses or advice on the selection of a thesis topic, please contact Maximilian Kentgens or Jonas Förster.
In the following, some open or ongoing work will be listed. In addition, there are always other possible workflows, which can be requested by the two above-mentioned contact persons. Just come by.
Open Theses
Adaptive Signalverarbeitung im Bereich Spatial Audio
Betreuer:Maximilian Kentgens
Themengebiet: Spatial Audio, Higher Order Ambisonics, Adaptive Signalverarbeitung
Characterization of Earbud-Mounted Accelerometers as Sensors for Speech Enhancement
Supervisors: Christoph Weyer
Area of work: Speech Enhancement, Headphone Technology, Acoustics
Characterization of the Body-Conduction of Speech for Hearables
Supervisors: Christoph Weyer
Area of work: Speech Enhancement, Headphone Technology, Acoustics
Betreuer:Tobias Kabzinski
Themengebiet: adaptive filters, signal processing, system identification
Investigations on Loudspeaker-based Adaptive Binaural Reproduction
Betreuer:Tobias Kabzinski
Themengebiet: signal processing, system identification, modeling, machine learning
Machine Learning zur Rekonstruktion verlorener Sprachsignalanteile
Betreuer: Lars Thieling
Themengebiet: Sprachsignalverarbeitung, Machine Learning
Motion Data-Supported Impulse Response Estimation
Betreuer:Tobias Kabzinski, Christoph Weyer
Themengebiet: signal processing, system identification, modeling
Multi-Microphone Speech Enhancement Techniques for Own Voice Estimation on Headphones and Earbuds
Supervisors: Christoph Weyer, Jonas Förster
Area of work: Speech Enhancement, Headphone Technology, Sensor Fusion, Acoustics
Signaladaptive Verbesserung räumlicher Audiosignale mit Hilfe von Stützmikrofonen
Betreuer:Maximilian Kentgens
Themengebiet: Spatial Audio, Higher Order Ambisonics, Adaptive Signalverarbeitung
Theses in progress
Investigation of Generative Neural Networks for Speech Enhancement
Betreuer:Lars Thieling, Till Hardenbicker
Themengebiet: Sprachsignalverarbeitung, Machine Learning
Investigations on Autoencoder Models for Online System Identification
Supervisors: Till Hardenbicker, Lars Thieling
Topics: System Identification, Manifold Learning, Neural Autoencoders