Detecting mental state from the user's speech

LARA GAUDER; FERRER, LUCIANA

Montevideo

Encuentro; Khipu; 2023

FACULTAD DE INGENIERÍA UNIVERSIDAD DE LA REPÚBLICA

We would like to present our work where we aim to explore the feasibility of automatically detecting the technical competence or ability of a virtual assistant (VA) from the user's speech. We developed a novel protocol for collecting speech data from subjects interacting with VAs with different skill levels. In consequence, we collected a new speech corpus in Argentine Spanish which is publicly available for research use. Using the collected data, we developed a system to detect the ability of the VA with which a subject interacted during a session, based on the subject's speech patterns.