![]() From several points of view, either purely computational (Brown, 1999 Brown et al., 2001) or purely perceptual (McAdams, 1993, 2013), it has been shown that the acoustic signal encompasses many indices specific to each instrument, which contribute to their recognition. Listeners' ability to recognize musical instruments has animated research for many years. Work on how humans do this could provide important insights concerning how to get machines to do it, as well to improve automatic annotation algorithms, for example. These results suggest that musical instrument timbres are characterized by specific spectrotemporal modulations, information which could contribute to music information retrieval tasks such as automatic source recognition.Īutomatic musical instrument recognition is one of the more complex problems in musical informatics research. Interestingly, instruments that were confused with each other led to non-overlapping regions and were confused when they were filtered in the most salient region of the other instrument. Globally, the instruments were correctly identified and the lower values of spectrotemporal modulations are the most important regions of the MPS for recognizing instruments. ![]() The method used here is based on a “molecular approach,” the so-called bubbles method. The most relevant regions of this representation for instrument identification were determined for each instrument and reveal the regions essential for their identification. The sounds were processed with filtered spectrotemporal modulations with 2D Gaussian windows. An identification task was applied to two subsets of musical instruments: tuba, trombone, cello, saxophone, and clarinet on the one hand, and marimba, vibraphone, guitar, harp, and viola pizzicato on the other. Nevertheless, the question of which specific regions of this representation characterize a musical instrument is still open. More recently, Modulation Power Spectra (MPS) have been shown to be a representation that potentially explains the perception of musical instrument sounds. It is now well known that the shapes of the temporal and spectral envelopes are crucial to the recognition of a musical instrument. The ability of a listener to recognize sound sources, and in particular musical instruments from the sounds they produce, raises the question of determining the acoustical information used to achieve such a task.
0 Comments
Leave a Reply. |