This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
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...
—The easiest way for a user to express his needs regarding a desired service is to use natural language. The main issues come from the fact that the natural language is incomplet...
Model Driven Engineering (MDE) proposes a software development process in which software is built by constructing one or more models, and transforming these into other models. In t...
Roxana S. Giandini, Claudia Pons, Gabriela P&eacut...
This paper introduces an executable coordination specification language, which is able to handle prespecified ways as well as more flexible and generic ways of specifying coordina...
Tibor Bosse, Mark Hoogendoorn, Radu Serban, Jan Tr...