vix.ing · top · new · best · stats · spec

Predicting interviewee attitude and body language from speech\n descriptors

2017/09/25 by Yosef A. Solewicz, Solewicz, Yosef, Chagay Orenshtein +3
Biochemistry, Genetics and Molecular Biology · Computer Science · #Animal Vocal Communication and Behavior #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1709.08344

openalex publication_date 2017/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This present research investigated the relationship between personal\nimpressions and the acoustic nonverbal communication conveyed by employees\nbeing interviewed. First, we investigated the extent to which different\nconversation topics addressed during the interview induced changes in the\ninterviewees' acoustic parameters. Next, we attempted to predict the observed\nand self-assessed attitudes and body language of the interviewees based on the\nacoustic data. The results showed that topicality caused significant deviations\nin the acoustic parameters statistics, but the ability to predict the personal\nperceptions of the interviewees based on their acoustic non-verbal\ncommunication was relatively independent of topicality, due to the natural\nredundancy inherent in acoustic attributes. Our findings suggest that joint\nmodeling of speech and visual cues may improve the assessment of interviewee\nprofiles.\n

Citations

Related