6533b850fe1ef96bd12a819e

RESEARCH PRODUCT

Tempo Induction from Music Recordings Using Ensemble Empirical Mode Decomposition Analysis

subject

description

Tempo and beat are among the most important features of Western music. Owing to the perceptual nature of tempo, its automatic analysis and extraction remains a difficult task for a large variety of music genres. Western music notation represents musical events using a hierarchical metrical structure distinguishing different time scales. This hierarchy is often modeled using three levels: the tatum, the tactus, and the measure. The tatum represents the shortest durational value in music that is not just an accidental phenomenon (Bilmes 1993). The tactus period is the most perceptually prominent period, and is the period at which most humans would tap their feet in time with the music (Lerdahl and Jackendoff 1983). The measure period is often related to the rate of harmonic change or the length of a repeated rhythmic pattern. This article deals with the estimation of the tempo at the tactus level. The tempo, which is the inverse of the tactus (beat) period, is expressed as the number of beats per minute (BPM). Tempo information is very important in many music information retrieval applications. Successful audio applications and music-analysis systems, such as video and audio editing software, cut-and-paste disk jockey applications, electronic instrument control, and synchronization, must be capable of analyzing and efficiently manipulating the rhythmic content of music. A review of different state-of-the art algorithms for tempo extraction from audio data is presented in the next section.