CTCModel: a Keras Model for Connectionist Temporal Classification
This work offers a domain-specific tool for researchers and practitioners in sequence labeling, but it is incremental as it primarily repackages existing methods into a more user-friendly framework.
The authors tackled the problem of implementing Connectionist Temporal Classification (CTC) for unsegmented sequence data by extending Keras with CTCModel, which provides transparent training, prediction, and evaluation branches using TensorFlow's CTC backend.
We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks, the Connectionist Temporal Classification is the reference method for dealing with unsegmented input sequences, i.e. with data that are a couple of observation and label sequences where each label is related to a subset of observation frames. CTCModel makes use of the CTC implementation in the Tensorflow backend for training and predicting sequences of labels using Keras. It consists of three branches made of Keras models: one for training, computing the CTC loss function; one for predicting, providing sequences of labels; and one for evaluating that returns standard metrics for analyzing sequences of predictions.