Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
Year: 2006
Type: article
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.
Authors: Alex Graves, Santiago Fernández, Faustino Gomez
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7027429494