In this pap er, we describe our speech understanding system and we test it on two different applications. The proposed system is a task specific one and it concern especially oral database consultation tasks. In this work, we consider that the automatic speech understanding problem could be seen as an association problem between two different languages. At the entry , the request expressed in natural language and at the end, just before the interpretation stage, the same request is expressed in term of concepts. A concept represents a given meaning, it is defined by a set of words sharing the same semantic properties. In this pap er, we propose a new Bayesian network based method to automatically extract the underlined concepts. We also propose and compare three approaches for the vector representation of words. We finish this pap er by a description of the post-processing step during which we generate corresponding SQL queries to the pronounced sentences and we connect our understanding system to a speech recognition engine. This step allows us to validate our speech understanding approach by obtaining with the two treated applications the rates of 78% and 81% of well formed SQL requests.