Abstract
This study introduces a methodological framework for constructing virtual ironic environments through the deliberate mismatching of emotional profiles in music and imagery. We conducted a statistical analysis of "happy/joy" and "angry" samples from two independent datasets to identify significant acoustic and visual features. These feature profiles were translated into mid-level semantic prompts to guide AI-based generation of visual and musical content. Our findings reveal distinct emotional signatures: happy music exhibits higher rhythmic onset rates and greater spectral variability, whereas angry music is characterized by a higher spectral centroid and more stable dissonance. Visually, joyful images are brighter and more symmetrical, while angry images feature darker hues and concentrated color distributions. Furthermore, mid-level perceptual descriptors generate the most coherent content, and we employed them to build a spectrum of virtual environments, including Sarcastic (joyful visuals + angry music) and Kind Ironic (angry visuals + happy music) spaces. This work establishes a new, data-driven approach to affective computing and speculative virtual design, grounded in the formal principle of audiovisual dissonance. © 2025 Copyright held by the owner/author(s).

Abstract

Abstract

Abstract
We present a novel physics-based concatenative sound synthesis (CSS) methodology for congruent interactions across physical, graphical, aural and haptic modalities in Virtual Environments. Navigation in aural and haptic corpora of annotated audio units is driven by user interactions with highly realistic photogrammetric based models in a game engine, where automated and interactive positional, physics and graphics data are supported. From a technical perspective, the current contribution expands existing CSS frameworks in avoiding mapping or mining the annotation data to real-time performance attributes, while guaranteeing degrees of novelty and variation for the same gesture.

Abstract

Abstract