In search of the role's footprints in client-therapist dialogues

Abstract

The goal of this research is to identify speaker's role via machine learning of broad acoustic parameters, in order to understand how an occupation, or a role, affects voice characteristics. The examined corpus consists of recordings taken under the same psychological paradigm (Process Work). Four interns were involved in four genuine client-therapist treatment sessions, where each individual had to train her therapeutic skills on her colleague that, in her turn, participated as a client. This uniform setting provided a unique opportunity to examine how role affects speaker's prosody. By a collection of machine learning algorithms, we tested automatic classification of the role across sessions. Results based on the acoustic properties show high classification rates, suggesting that there are discriminative acoustic features of speaker's role, as either a therapist or a client.

Is human-human spoken interaction manageable? The emergence of the concept: ‘Conversation Intelligence’

“…Moreover, the comparison of the three sessions to session BM demonstrates that the role of the speaker does not necessarily entail the participation level, and therefore power relations cannot directly be derived from these durational parameters. In Lerner, Silber-Varod, Batista, and Moniz (2016), we examined the same sessions in a more complex way, using computational learning methods on acoustic parameters. We found that at the beginning of each session there were more differences in the acoustic variables between the two speakers than there were in the middle of the session while the least differences were found at the final part of the session.…”