Figure 5From: The self-taught vocal interfaceHierarchical, compositional and flat structures. Hierarchical against compositional frame structure for PATCOR in the upper part, and the compositional against the flat structure for DOMOTICA-3 in the lower part. Numbered circles represent speaker ID, and their locations indicate F-scores as a function of the number of utterances in the training sets. Furthermore, the smoothed curves are interpolations of the scattered F-scores using the LOWESS procedure, and they exemplify the performance of an average speaker.Back to article page