Laughter is a paralinguistic phenomenon widely used in human communication. Previous studies on laughter have mainly looked at its acoustic realization and its functions, leaving the context in which laughter occurs relatively under-studied. We intend to partially fill this gap by conducting an investigation into the acoustic cues that mark the use of laughter. We focus on the syllables preceding laughter and we explore several relevant spectral features. The results obtained on an American English corpus of conversational speech show anticipatory effects on the syllable immediately preceding laughter: a higher F1, a higher spectral center of gravity and a greater spectral standard deviation. We discuss these findings in terms of the individual variation present in laughter.