Connectionist Temporal Classification, Labelling Unsegmented Sequence Data with RNN | TDLS
Toronto Deep Learning Series, 9 July 2018
For slides and more information, visit https://tdls.a-i.science/events/2018-...
Paper Review: https://www.cs.toronto.edu/~graves/ic...
Speaker: / waseem-gharbieh-2432234b
Organizer: / amirfz
Host: https://www.shopify.ca/careers
Paper abstract:
"Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is transcribed into words or sub-word units. Recurrent neural networks (RNNs) are powerful sequence learners that would seem well suited to such tasks. However, because they require pre-segmented training data, and post-processing to transform their outputs into label sequences, their applicability has so far been limited. This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems. An experiment on the TIMIT speech corpus demonstrates its advantages over both a baseline HMM and a hybrid HMM-RNN."