Mismatch between training and test conditions deteriorates the performance of speech recognizers. This paper investigates the combination of parametric histogram equalization (pHE...
This paper addresses the detection of OOV segments in the output of large vocabulary continuous speech recognition (LVCSR) system. First, standard confidence measures based on fr...
Lukas Burget, Petr Schwarz, Pavel Matejka, Mirko H...
In an attempt to overcome problems associated with articulatory limitations and generative models, this work considers the use of phonological features in discriminative models fo...
A conditional model is introduced for triggering understanding actions that correct errors of frame hypothesization and composition. Experimental evidence is provided using the Fr...
Abstract. Natural audio-visual interface between human user and machine requires understanding of user’s audio-visual commands. This does not necessarily require full speech and ...