The Cyclic Beat Spectrum: Tempo-Related Audio Features for Time-Scale Invariant Audio Identification

In this paper, we present a novel set of tempo-related audio features for applications in audio retrieval. As opposed to existing feature sets commonly used in the retrieval domain which mainly focus on local spectral characteristics of the audio signal, our features capture its local temporal behaviour w.r.t. tempo, rhythm, and meter. As a key component to obtaining a high level of feature robustness we introduce the cyclic beat spectrum (CBS) consisting of residual tempo classes which are constructed similarly to the wellknown pitch chroma classes. We illustrate the use of the newly constructed features by applying them to robust timescale invariant audio identification.