Project CUIDADO, French PRIAMM Project ECRINS, and French Oseo Project QUAERO grants to Geoffroy Peeters at Ircam, and grants from the Natural Sciences and Engineering Research Council of Canada and the Canada Research Chair program to S.M. This research was supported by European ESPRIT 28793 Project Cuidad, European I.S.T. This analysis suggests ten classes of relatively independent audio descriptors, showing that the Timbre Toolbox is a multidimensional instrument for the measurement of the acoustical structure of complex sound signals. To examine the information redundancy across audio descriptors, correlational analysis followed by hierarchical clustering is performed. Robust descriptive statistics are used to characterize the time-varying descriptors. Some descriptors are global, providing a single value for the whole sound event, whereas others are time-varying. A large number of audio descriptors are then derived from each of these representations to capture temporal, spectral, spectrotemporal, and energetic properties of the sound events. Sound events are first analyzed in terms of various input representations (short-term Fourier transform, harmonic sinusoidal components, an auditory model based on the equivalent rectangular bandwidth concept, the energy envelope). The Timbre Toolbox provides a comprehensive set of descriptors that can be useful in perceptual research, as well as in music information retrieval and machine-learning approaches to content-based retrieval in large sound databases. The analysis of musical signals to extract audio descriptors that can potentially characterize their timbre has been disparate and often too focused on a particular small set of sounds.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |