This paper addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...
The ever-growing use of modeling languages today is largely due to a maturation of model-based development technologies. However, there is enough room for improving language specif...
Abstract—In this paper we introduce Timed Moore Automata, a specification formalism which is used in industrial train control applications for specifying the real-time behavior ...
A business process model represents the basic building block for a workflow-enabled enterprise information system. Generally, a process model evolves through numerous changes durin...
Abstract. A genetic algorithm is used to learn a non-deterministic Petri netbased model of non-linear gene interactions, or statistical epistasis. Petri nets are computational mode...