2 papers
eess.AS2023
Stabilizing Training with Soft Dynamic Time Warping: A Case Study for Pitch Class Estimation with Weakly Aligned Targets
Johannes Zeitler, Simon Deniffel, Michael Krause +1
Soft dynamic time warping (SDTW) is a differentiable loss function that allows for training neural networks from weakly aligned data. Typically, SDTW is used to iteratively compute…
cs.SD2023
Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond
Michael Krause, Christof Weiß, Meinard Müller
Many tasks in music information retrieval (MIR) involve weakly aligned data, where exact temporal correspondences are unknown. The connectionist temporal classification (CTC) loss…