The evaluation of auditory brainstem responses (ABRs) is accepted to be the most reliable method for the objective diagnosis and quantification of hearing loss in newborns. However, in currently available setups and devices, a large number of sweeps has to be averaged to obtain a meaningful signal at low stimulation levels due to a poor signal-to-noise ratio. Due to the time consuming averaging procedure which requires the state of spontaneous sleep, sedation, or narcosis of the newborns, the evaluation of ABRs can only be used at the last stage of area-wide universal newborn hearing screening programs, increasing their implementation cost significantly and thus making their realization impossible in many cases.Here we propose a new novelty detection paradigm for the fast detection of hearing thresholds using the synchronization stability of auditory brainstem response single sweeps. For this, large-scale correlates of the neural group synchronization at the brainstem level by a stimulation level above the hearing threshold are detected as novel event. This novelty detection paradigm allows for the adaptive inclusion of individual measurement conditions using the spontaneous EEG. For the individual patient, at the challenging stimulation level of 30dB(HL) the synchronization stability allowed the discrimination of stimulated from the non-stimulated condition in a fraction of time of conventional devices used for newborn hearing screening.It is concluded that the proposed method might be used for the ultra-fast detection of hearing thresholds and is thus ideally suited for universal hearing screening programs.