Most of modern advertisements contain a song to illustrate the commercial message. The success of a product, and its economic impact, can be directly linked to this choice. Finding the most appropriate song is usually made manually. Nonetheless, a single person is not able to listen and choose the best music among millions. The need for an automatic system for this particular task becomes increasingly critical. This paper describes the LIA music recommendation system for advertisements using both tex-tual and acoustic features. This system aims at providing a song to a given commercial video and was evaluated in the context of the MediaEval 2013 Soundtrack task [14]. The goal of this task is to predict the most suitable soundtrack from a list of candidate songs, given a TV commercial. The organizers provide a development dataset including multimedia features. The initial assumption of the proposed system is that commercials which sell the same type of product, should also share the same music rhythm. A twofold system is proposed: find commercials with close subjects in order to determine the mean rhythm of this subset , and then extract, from the candidate songs, the music which better corresponds to this mean rhythm.