Spectral Frequency Tracking for Classifying Audio Signals

Taniguchi et al. proposed a sinusoidal decomposition framework for classifying audio sounds. In this framework, spectral tracking is important, yet still presents an unsolved problem, although it has been investigated for the purpose of sound synthesis or sound modification. Conventional methods developed for these purposes are either ad hoc and less computationally complex or not ad hoc but more computationally complex. In this paper, we propose an optimal and less computationally complex method based on dynamic programming and iterative improvement. We have evaluated this method in experiments using synthesized sound and found that it works well