The aim of this document is to discuss possible ways of describing some music constructs in a dual context. First, that of the current standard for multimedia content description: MPEG-7. Second, that of a specific so,are application, the Sound Palette (a tool for content-based management, content edition and transformation of simple audio phrases). We discuss some MPEG-7 limitations regarding different musical layers: melodic (present but underdeveloped), rhythmic (practically absent) and instrumental (present though using an exclusive procedure). Some proposals for overcoming them are presented in the context of our application.

We present a plugin implementation for the multi-platform Wave-Surfer sound editor. Added functionalities are the semi-automatic extraction of beats at diverse levels of the metrical hierarchy as well as uploading and downloading functionalities to a music metadata database. It is built upon existing open source (GPL-licenced) audio processing tools, namely WaveSurfer, BeatRoot and CLAM, in the intent to expand the scope of those softwares. It is therefore also provided as GPL code with the explicit goal that researchers in the audio processing community can freely use and improve it. We provide technical details of the implementation as well as practical use cases. We also motivate the use of rhythmic metadata in Music Information Retrieval scenarios. 1.

this paper, we rather choose to restrain ourselves to energy features. The reason for this is our aim to test the common assumption in the literature that they would represent su#ciently well the rhythmic aspects of musical signals. Testing other features is left to future work

This paper presents and compares two methods of tracking the beat in musical performances, one based on a Bayesian decision framework and the other a gradient strategy. The techniques can be applied directly to a digitized performance (i.e., a soundfile) and do not require a musical score or a MIDI transcription. In both cases, the raw audio is first processed into a collection of “rhythm tracks” which represent the time evolution of various low-level features. The Bayesian approach chooses a set of parameters that represent the beat by modeling the rhythm tracks as a concatenation of random variables with a patterned structure of variances. The output of the estimator is a trio of parameters that represent the interval between beats, its change (derivative), and the position of the starting beat. Recursive (and potentially real time) approximations to the method are derived using particle filters, and their behavior is investigated via simulation on a variety of musical sources. The simpler method, which performs a gradient descent over a window of beats, tends to converge more slowly and to undulate about the desired answer. Several examples are presented that highlight both the strengths and weaknesses of the approaches.