Reinterpreting CTC training as iterative fitting
作者：
Highlights：
• We rewrite the CTC objective function as the frame-wise cross-entropy, and reinterpret CTC training as a heuristic algorithm. This is a brand new perspective and a more intuitive way to understand and modify CTC.
• From the new perspective, we modify CTC training in two ways. (1) Specify the proportion of non-blank labels to solve the spiky problem of CTC. (2) Reweight the frames within each sequence to speed up convergence.
• We provide a tool that simulates and visualizes the training process of CTC, on which we can perform modification and peek its effects on CTC training. This enables us to exclude some useless modifications in advance, which saves lots of time.
摘要
•We rewrite the CTC objective function as the frame-wise cross-entropy, and reinterpret CTC training as a heuristic algorithm. This is a brand new perspective and a more intuitive way to understand and modify CTC.•From the new perspective, we modify CTC training in two ways. (1) Specify the proportion of non-blank labels to solve the spiky problem of CTC. (2) Reweight the frames within each sequence to speed up convergence.•We provide a tool that simulates and visualizes the training process of CTC, on which we can perform modification and peek its effects on CTC training. This enables us to exclude some useless modifications in advance, which saves lots of time.
论文关键词：Connectionist temporal classification (CTC)
论文评审过程：Received 4 May 2019, Revised 23 March 2020, Accepted 21 April 2020, Available online 26 April 2020, Version of Record 12 May 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107392
