A biomimetic multi-resolution spectrotemporal model for musical timbre recognition.
Kailash Patil, Mounya Elhilali · The Journal of the Acoustical Society of America · 2010
Timbre is usually defined as that property of sound that is neither pitch nor loudness that helps in identifying sounds. Such a definition of what it is not is in itself problematic and unsatisfactory. The complexity of characterizing a timbre space stems from the intricate interactions between spectrotemporal dynamics of sound, which overcasts the simple description of individual acoustic dimensions as usually captured by techniques such as multidimensional scaling. By contrast, sound encoding in the mammalian auditory system, and particularly its sensitivity to spectrotemporal modulations, offers a rich feature space to explore perceptual representations of timbre. In the present work, the problem of musical timbre modeling was casted as a generative model based on a reduced set of multi-resolution spectrotemporal features inspired from encoding of complex sound in the auditory cortex. A probabilistic system based on Gaussian mixtures was built to perform a timbre recognition task on a data set consisting of 12 instruments. The system was able to achieve an accuracy of 98%, hence corroborating the claim that physiologically inspired features are effective in properly outlining a timbre space. These results could have significant implications in terms of better understanding the neural correlates of timbre perception.