The content in this documentation section concerns with the plug-in version of PENTAtrainer2. Users can download the user manual of the script version from here.

The following diagram illustrates the workflow for prosody modeling using PENTAtrainer2. It consists of three computational tools: Annotation, Learning and Synthesis tools. The first step in prosody modeling (1) is to annotate the corpus with the Annotation tool. Before the annotation, users need to determine the number of communicative/linguistic functions that will be studied, as well as their internal categories. This annotation step is the most time consuming part for the user. In this step, users need to mark the boundaries in each layer associating with a particular factor and name the category in each interval. In the second step (2), parameters are automatically optimized by the Learning tool. This step requires user input only on a few optimization parameters. The speed of optimization process depends on the size of the corpus, the number of functional combinations, and the above-mentioned optimization parameters. In the last step (3), i.e., after the optimization process is completed, users can use the Synthesis tool to synthesize F0 contours based on the optimized parameters and visually compare them to the originals.