A.: Using source separation to improve tempo detection

We describe a novel tempo estimation method based on decomposing musical audio into sources using principal latent component analysis (PLCA). The approach is moti-vated by the observation that in rhythmically complex mu-sic, some layers may be more rhythmically regular than the overall mix, thus facilitating tempo detection. Each excerpt was analyzed using PLCA and the resulting components were each tempo tracked using a standard autocorrelation-based algorithm. We describe several techniques for ag-gregating or choosing among the multiple estimates that result from this process to extract a global tempo estimate. The system was evaluated on the MIREX 2006 training database as well as a newly constructed database of rhyth-mically complex electronic music consisting of 27 exam-ples (IDM DB). For these databases the algorithms im-proved accuracy by 10 % (60 % vs 50%) and 22.3 % (48.2% vs. 25.9%) respectively. These preliminary results suggest that for some types of music, source-separation may lead to better tempo detection. 1