Alex Graves, Santiago Fernandez, Faustino Gomez, Jurgen Schmidhuber. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In ICML '06 Proceedings of the 23rd international conference on Machine learning, pp. 369-376, 2006.
Download preprint: not available
Download from publisher: https://dl.acm.org/citation.cfm?id=1143891
Related web page: not available
Bibliography entry: BibTeX
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.