Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Deniffel, Simon"'
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 and refine soft alignments that compensate for temporal deviations be
Externí odkaz:
http://arxiv.org/abs/2308.05429