#47 Automatic Segmentation of the Temporal Evolution of Isolated Acoustic Musical Instruments Sounds Using Spectro-Temporal Cues
Marcelo Caetano, Juan José Burred, Xavier Rodet
The automatic segmentation of isolated musical instrument sounds according to the temporal evolution is not a trivial task. It requires a model capable of capturing regions such as the attack, decay, sustain and release accurately for many types of instru-ments with different modes of excitation. The traditional ADSR amplitude envelope model does not apply universally to acoustic musical instrument sounds with different excitation methods be-cause it uses strictly amplitude information and supposes all sounds manifest the same temporal evolution. We present an automatic segmentation technique based on a more realistic model of the temporal evolution of many types of acoustic musi-cal instruments that incorporates both temporal and spectro-temporal cues. The method allows a robust and more perceptu-ally relevant automatic segmentation of the isolated sounds of many musical instruments that fit the model.