Acoustic Markers of Emotion Based on Voice Physiology

Sona Patel, Klaus R. Scherer, Johan Sundberg, Eva Björkner, Swiss Center for Affective Sciences (CISA), University of Geneva

Acoustic models of emotional expressions may benefit from considering the underlying voice production mechanism. This study sought to describe emotional expressions according to the physiological changes measured from the inverse-filtered glottal waveform in addition to standard parameter extraction. An acoustic analysis was performed on a subset of the /a/ vowels within the GEMEP database (10 speakers, 5 emotions). Of the 12 parameters computed, repeated measures ANOVA showed significant main effects for 11 of these cues. Subsequent principal components analysis revealed three components to explain acoustic variations in emotion, including “tension” (CQ, H1-H2, MFDR, and LTAS) “perturbation” (jitter, shimmer, and HNR), and “voicing” (fundamental frequency).