In the area of large speech corpora, there is a definite need for common prosodic notation system based on efficient (semi)- automating tools of prosodic segmentation and labelling. In this context, we present the software program ANALOR, developed in order to process semi-automatically prosodic data. From a text-sound alignment, this computer tool detects major prosodic units, on the basis of global and local melodic variations. That leads to the segmentation of an utterance in prosodic periods. Inside those prosodic periods, prominent syllables are then automatically detected. 1. Introduction