What: Experimentally elicited monologues are highly informative of the mental disorders and symptoms of the speakers (cf. Clinical Voices previous project). Here we aim at developing the techniques to apply these methods and findings to naturalistic conversations. Combining methods developed during the Clinical Voices (IMC, AU) and the Speechome (MIT) projects we aim at automatically coding turn-taking strategies and interlocutors in naturally occurring conversations collected during the Clinical Voices project and by the UConn Child Language Lab. These materials will then be analyzed in terms of language and movement recurrence in the individuals’ behavior, across individuals and in the conversation as a whole. Machine learning will be used on the features individuated to develop automatic assessment of the interactional patterns in their relation to mental disorders.
Effektiv start/slut dato06/01/2014 → …


Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.