We propose the use of the line spectral frequency (LSF) features for emotion recognition from speech, which have not been been previously employed for emotion recognition to the b...
Many conventional human detection methods use features based on gradients, such as histograms of oriented gradients (HOG), but human occlusions and complex backgrounds make accurat...
This paper investigates the use of speech-to-text methods for assigning an emotion class to a given speech utterance. Previous work shows that an emotion extracted from text can c...
Florian Metze, Anton Batliner, Florian Eyben, Tim ...
With millions of teenagers on the Internet, millions of parents are trying to understand what their teens are doing and why. Understanding how technology use impacts teens‘ lear...
We present universal earphones that use both a proximity sensor and a skin conductance sensor and we demonstrate several implicit interaction techniques they achieve by automatica...