The Adjustment/Satisfaction Test (A/ST) for the Evaluation of Personalization in Broadcast Services and Its Application to Dialogue Enhancement

Source Separation for Enabling Dialogue Enhancement in Object-based Broadcast with MPEG-H

“…These observations confirm the results obtained in [10], where the same system S BSS was tested using stereo material with speech panned to the center, i.e., S BSS could exploit also stereo methods such as PAD and CE. Fig.…”

“…Methodology. In [10] we presented the Adjustment/Satisfaction Test (A/ST) where the participants interact with a user-adjustable system and their adjustments and the resulting satisfaction levels are studied. This allows analyzing to what extent the available personalization is used and quantifying the quality of experience improvement.…”

“…After the adjustment, the participants are asked to rate the difference in satisfaction between the initial mix and the personalized version. The satisfaction is assessed directly after adjusting each item, i.e., using the "Experience configuration" from [10]. Stimulus.…”

“…The underlying reason for low intelligibility may be, e.g., hearing impairment [2], challenging listening environment [3], non-ideal reproduction setup [4], listener's language skill level in the dialogue language [5,6], or unfamiliar accent or dialect [7,8]. Even when the intelligibility is not compromised, the personal preference of the listener may differ from the broadcast mix [9,10].…”

“…d e A R 4 _ e n A R 1 _ d e T V 3 _ e n A R 3 _ d e a v g it e m S a m e a s S li g h tl y b .Previous evaluation with stereo material and speech panned to the center C 2018 IEEE. Reprinted, with permission, from[10].…”