Modern optical character recognition software relies on human interaction to correct misrecognized characters. Even though the software often reliably identifies low-confidence ...
Michael L. Wick, Michael G. Ross, Erik G. Learned-...
Probabilistic latent semantic analysis is enhanced with long distance bigram models in order to improve word clustering. The long distance bigram probabilities and the interpolate...
In this paper we discuss the use of discourse context in spoken dialogue systems and argue that the knowledge of the domain, modelled with the help of dialogue topics is important...
This paper presents an approach to estimating word level prominence in Swedish using syllable level features. The paper discusses the mismatch problem of annotations between word ...
A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dim...