Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
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...
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
Georg Heigold, Geoffrey Zweig, Xiao Li, Patrick Ng...
Large vocabulary automatic speech recognition (ASR) technologies perform well in known and controlled contexts. In less controlled conditions, however, human review is often neces...
Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfi...