A virtual reality tool to aid in soundscapes in the built environment (SiBE) through machine learning

Abstract

Regarding the function and context of the space, virtual reality (VR) can be used for soundscapes design if the user behavior is predictable. This study enables the acoustic characterization of VR development tools to measure auditory perception based on user behavior. The research question is whether soundscapes can be modeled according to the variable acoustic environments defined by the existing architectural features (e.g., prismatic, courtyard, vault, arched, mezzanine). A sound simulation algorithm in MATLAB was developed to extract room impulse response (RIR) of the test environment in a virtual environment and to compare it with the real environment (RE). In the developed program, image source model (ISM) and ray trace were used to be performed the real-time acoustic source generation and real-time signal recording, image functions, data processing, metric calculation operations (e.g., tonality and spectrogram). B&K 4292 omni-power loudspeaker, B&K 2716 power amplifier, and B&K 2250 hand-held analyzer were used to measure RIR in the RE. In addition to RIR and RT30, psychoacoustic metrics (e.g., loudness, sharpness, roughness, and fluctuation strength) were measured in both environments. The results showed that sound simulation, based on ISM, demonstrates the validity and can be used for the acoustic characterization of VR development environments.