Language is often perceived together with visual information. Recent experimental evidences indicated that, during spoken language comprehension, the brain can immediately integrate visual information with semantic or syntactic information from speech. Here we used the mismatch negativity to further investigate whether prosodic information from speech could be immediately integrated into a visual scene context or not, and especially the time course and automaticity of this integration process. Sixteen Chinese native speakers participated in the study. The materials included Chinese spoken sentences and picture pairs. In the audiovisual situation, relative to the concomitant pictures, the spoken sentence was appropriately accented in the standard stimuli, but inappropriately accented in the two kinds of deviant stimuli. In the purely auditory situation, the speech sentences were presented without pictures. It was found that the deviants evoked mismatch responses in both audiovisual and purely auditory situations; the mismatch negativity in the purely auditory situation peaked at the same time as, but was weaker than that evoked by the same deviant speech sounds in the audiovisual situation. This pattern of results suggested immediate integration of prosodic information from speech and visual information from pictures in the absence of focused attention.