Validation of Scrambling Methods for Vocal Affect Bursts

Abstract

Studies on perception and cognition require sound methods allowing to disentangle basic sensory processing of physical stimulus properties and the cognitive processing of the meaning of a stimulus. Similar to image scrambling, the scrambling of auditory signals aims at creating stimulus instances that are not recognizable but have comparable low-level features. In the present study, we generated scrambled stimuli of short vocalizations taken from the Mon-treal Affective Voices database (Belin et al., 2008, Behav Res Methods, 40) by applying four different scrambling methods (frequency-, phase-, and two time-scrambling transformations). The original stimuli and scrambled versions were judged by N = 60 participants for the appar-ency of a human voice, gender, and valence of the expressions, or if no human voice was de-tected, for the valence of the subjective response toward the stimulus. The human-likeness rat-ings were reduced for all scrambled versions compared to the original stimuli, albeit to a lesser degree for phase-scrambled versions of neutral bursts. For phase-scrambled neutral bursts, va-lence ratings were equivalent to the ratings of the original neutral burst. All other scrambled versions were rated as slightly unpleasant, indicating that they should be used with caution due to their potential aversiveness.