InterSpeech 2021

ThemePro 2.0: Showcasing the Role of Thematic Progression in Engaging Human-Computer Interaction
(longer introduction)

Mónica Domínguez (Universitat Pompeu Fabra, Spain), Juan Soler-Company (Universitat Pompeu Fabra, Spain), Leo Wanner (Universitat Pompeu Fabra, Spain)
Structuring speech into informative units is certainly a desirable feature in efficient human-machine communication. This paper introduces ThemePro 2.0, a toolkit that pre-processes long monologues into smaller cohesive units to be consumed by the text-to-speech module within a conversational agent. The methodology used is based upon the text’s discourse structure modelled as thematic progression patterns. As shown in the demonstration, thematic progression modelling captures the underlying information structure at the discourse level and is, therefore, instrumental for cohesive speech output in the TTS component.