CALLIOPE: A multi-dimensional model for the prosodic characterisation of Information Units

CALLIOPE is a conceptual multi-dimensional model that aims at approximating and categorising the prosodic phenomena. Its goal is to provide a method suitable for the analysis of dialogue and dialogic interaction, and the design of vocal corpora usable in the development of deep learning algorithms, merging theories belonging to different research fields on human language. CALLIOPE contains all possible independent factors affecting the sound of so-called Information Units (IUs). In CALLIOPE, each IU is associated with a tuple composed of 12 labels, where each of them belongs to a different dimension representing a characteristic influencing the prosodic behaviour. These dimensions are divided into two groups: the first one containing fully defined characteristics directly related to the dialogic dimension (e.g. Motivational state, Rhetorical form, etc.), while the second one takes into account dimensions that exist regardless of the presence of interaction (e.g. Language or dialect, social context, etc.).