Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks

Many real-world sequence learning tasks requirethe prediction of sequences of labelsfrom noisy, unsegmented input data. Inspeech recognition, for example, an acousticsignal is transcribed into words or sub-wordunits. Recurrent neural networks (RNNs) arepowerful sequence learners that would seemwell suited to such tasks. However, becausethey require pre-segme..