Validating a perceptual distraction model in a personal two-zone sound system

This paper focuses on validating a perceptual distraction model, which aims to predict user’s perceived distraction caused by audio-on-audio interference, e.g., two competing audio sources within the same listening space. Originally, the distraction model was trained with music-on-music stimuli using a simple loudspeaker setup, consisting of only two loudspeakers, one for the target sound source and the other for the interfering sound source. Recently, the model was successfully validated in a complex personal sound-zone system with speech-on-music stimuli. Second round of validations were conducted by physically altering the sound-zone system and running a set of new listening experiments utilizing two sound zones within the sound-zone system. Thus, validating the model using a different sound-zone system with both speech-on-music and music-on-speech stimuli sets. Preliminary results show that the model performance is equally good in both zones, i.e., with both speech-on-music and music-on-speech stimuli, and comparable to the previous validation round (RMSE approximately 10%). The results further confirm that the distraction model can be used as a valuable tool in evaluating and optimizing the performance of personal sound-zone systems.