Connectionist temporal classification

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.

Keywords

TIMITComputer scienceSpeech recognitionRecurrent neural networkConnectionismHidden Markov modelSequence (biology)Artificial intelligenceWord (group theory)Sequence labelingPattern recognition (psychology)Artificial neural networkNatural language processingMathematics

Affiliated Institutions

Related Publications

Learning the hidden structure of speech

Jeffrey L. Elman , David Zipser

In the work described here, the backpropagation neural network learning procedure is applied to the analysis and recognition of speech. This procedure takes a set of input/outpu...

1988 The Journal of the Acoustical Society... 269 citations

An exploration of large vocabulary tools for small vocabulary phonetic recognition

Tara N. Sainath , Bhuvana Ramabhadran , Michael Picheny

While research in large vocabulary continuous speech recognition (LVCSR) has sparked the development of many state of the art research ideas, research in this domain suffers fro...

2009 33 citations

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath , Bhuvana Ramabhadran , Michael Picheny +2 more

The use of exemplar-based methods, such as support vector machines (SVMs), k-nearest neighbors (kNNs) and sparse representations (SRs), in speech recognition has thus far been l...

2011 IEEE Transactions on Audio Speech and... 65 citations

Global optimization of a neural network-hidden Markov model hybrid

Yoshua Bengio , Renato De Mori , Giovanni Flammia +1 more

An original method for integrating artificial neural networks (ANN) with hidden Markov models (HMM) is proposed. ANNs are suitable for performing phonetic classification, wherea...

2002 18 citations

Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

Brian Kingsbury

Acoustic models used in hidden Markov model/neural-network (HMM/NN) speech recognition systems are usually trained with a frame-based cross-entropy error criterion. In contrast,...

2009 238 citations

Publication Info

Year: 2006
Type: article
Pages: 369-376
Citations: 5199
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Connectionist temporal classification

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

5199

OpenAlex

Cite This

APA Style

                            
                                    Alex Graves, 
                                
                                    Santiago Fernández, 
                                
                                    Faustino Gomez
                                
                                et al.
                            
                            (2006). 
                            Connectionist temporal classification. 
                            
                            , 369-376.
                            https://doi.org/10.1145/1143844.1143891

Identifiers

DOI: 10.1145/1143844.1143891