Gesture recognition enables a natural extension of the way we currently interact with devices. Commercially available gesture recognition systems are usually pre-trained. We propose a method that allows users to define their own gestures using only a few training examples.
We develop a fully probabilistic approach to pure-tone audiometry. By assuming a Gaussian process based response model for test tones, the hearing threshold estimation problem becomes one of Bayesian inference. This allows the use of information-theoretic criteria to select optimal test tones.
We want to provide a hearing impaired patient with the best setting for her hearing aid device. By recording in-situ user feedback on device performance, we are able to better understand the specific hearing loss problem and preferences of the user. Using this knowledge, we can provide a better and personalized hearing experience.
How do you solve a problem that is only vaguely described? We describe here an engineering approach that guides our research on solving vaguely defined problems such as hearing impairment.
This research program is aimed at developing modern machine learning methods that lead to improved design of signal processing algorithms, e.g., for audio processing or quantified-self applications.
In this project, you are challenged to develop novel machine learning technology for recognizing human motions.
In this project, you are challenged to design an agent that learns to solve the cocktail party problem through on-the-spot interactions with a (human) listener.