Star Temporal Classification: Sequence Classification with Partially Labeled Data
This addresses the challenge of training sequence models with incomplete labels, which is incremental as it builds on existing methods like CTC.
The paper tackles the problem of learning from partially labeled and unsegmented sequential data by introducing Star Temporal Classification (STC), which recovers most of the performance of a supervised baseline when up to 70% of labels are missing in automatic speech recognition experiments.
We develop an algorithm which can learn from partially labeled and unsegmented sequential data. Most sequential loss functions, such as Connectionist Temporal Classification (CTC), break down when many labels are missing. We address this problem with Star Temporal Classification (STC) which uses a special star token to allow alignments which include all possible tokens whenever a token could be missing. We express STC as the composition of weighted finite-state transducers (WFSTs) and use GTN (a framework for automatic differentiation with WFSTs) to compute gradients. We perform extensive experiments on automatic speech recognition. These experiments show that STC can recover most of the performance of supervised baseline when up to 70% of the labels are missing. We also perform experiments in handwriting recognition to show that our method easily applies to other sequence classification tasks.