A process for scanning and/or synchronizing audio/video events is described. According to the process, a signal is acquired and divided into a plurality of segments corresponding to different moments of the signal. A spectrogram is generated and peaks are located in the spectrogram. Transition peaks are located among said peaks, and the bands of such transition peaks are combined in one or more transitions to which hashes correspond. The hashes are associated with the time at which the transitions occur in the signal. Means for scanning and/or synchronizing audio/video events are also disclosed.