Jan Stadermann

Tied-Posteriors: A New Hybrid Speech Recognition Technology with Generic Capabilities and High Portability (2007)

Jan Stadermann, Jörg Rottland, J Org Rottl, Gerhard Rigoll

This paper presents a new method for estimating the emission probabilities of general hybrid connectionist/HMM recognition systems. Contrary to the traditional hybrid approach, where a neural network...

COMPARISON OF STANDARD AND HYBRID MODELING TECHNIQUES FOR DISTRIBUTED SPEECH RECOGNITION (2007)

Jan Stadermann, Gerhard Rigoll

Distributed speech recognition (DSR) is an interesting technology for mobile recognition tasks where the recognizer is split up into two parts and connected with a transmission channel. We compare...

Automatische Spracherkennung mit hybriden akustischen Modellen (2007)

Stadermann, Jan

Das akustische Modell eines Spracherkenners basiert auf Methoden der statistischen Mustererkennung, um eine parametrische Repräsentation der gesprochenen Äußerung zu ermöglichen. Zusammen mit...

Constructing synthetic faces using Active Appearance Models and evaluating the similarity to the original image data (2006)

Andre Störmer, Jan Stadermann

Active Appearance Models (AAMs) can be used for interpreting face images and image sequences. AAMs combine a statistical shape model and a model of grey-level appearance. They also contain an...