Stabilizing Training with Soft Dynamic Time Warping: A Case Study for Pitch Class Estimation with Weakly Aligned Targets

1 code implementation • 10 Aug 2023 • Johannes Zeitler, Simon Deniffel, Michael Krause, Meinard Müller

Typically, SDTW is used to iteratively compute and refine soft alignments that compensate for temporal deviations between the training data and its weakly annotated targets.

Dynamic Time Warping Scheduling