This paper presents a preliminary study on the relation between audiovideo streams and high-level information related to expressive nuances. A violinist was asked to play three musical excerpts several times, each one inspired by one of nine different expressive intentions. Perceptual tests was carried out using both audio-only and audio-visual recordings of the performances. The results demonstrate that the visual component aids the subjects to better recognize the different expressive intentions of the musical performances, showing that the fusion of audio-visual information can significantly improve the degree of recognition
given by single means.
