Previous research on automatic laughter detection has mainly been focused on audio-based detection. In this study we present an audiovisual approach to distinguishing laughter from speech and we show that the integration of audio and visual information leads to improved performance over single-modal approaches. We consider two cases, one that we discriminate between laughter and speech and one that we discriminate between voiced laughter, unvoiced laughter and speech. When tested on 207 audiovisual sequences, depicting spontaneously displayed (as opposed to posed) laughter and speech episodes, in a person independent way the proposed audiovisual approach achieves an F1 rate of over 90% and a classification rate of over 80%.