Acoustic Modeling Using Deep Belief Networks

Abstract

Gaussian mixture models are currently the dominant technique for modeling the emission distribution of hidden Markov models for speech recognition. We show that better phone recognition on the TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of parameters. These networks are first pre-trained as a multi-layer generative model of a window of spectral feature vectors without making use of any discriminative information. Once the generative pre-training has designed the features, we perform discriminative fine-tuning using backpropagation to adjust the features slightly to make them better at predicting a probability distribution over the states of monophone hidden Markov models.

Keywords

TIMITHidden Markov modelDiscriminative modelComputer scienceArtificial intelligencePattern recognition (psychology)Deep belief networkMixture modelArtificial neural networkSpeech recognitionFeature (linguistics)BackpropagationFeature extractionMarkov modelGenerative modelGaussianGenerative grammarMachine learningMarkov chain

Affiliated Institutions

University of Toronto CA

Related Publications

Deep Belief Networks using discriminative features for phone recognition

Abdelrahman Mohamed , Tara N. Sainath , George E. Dahl +3 more

Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fe...

2011 289 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

Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition

Ossama Abdel‐Hamid , Abdelrahman Mohamed , Hui Jiang +1 more

Convolutional Neural Networks (CNN) have showed success in achieving translation invariance for many image processing tasks. The success is largely attributed to the use of loca...

2012 885 citations

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Geoffrey E. Hinton , Li Deng , Dong Yu +8 more

Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well ...

2012 IEEE Signal Processing Magazine 10065 citations

Backpropagation training for multilayer conditional random field based phone recognition

Rohit Prabhavalkar , Eric Fosler‐Lussier

Conditional random fields (CRFs) have recently found increased popularity in automatic speech recognition (ASR) applications. CRFs have previously been shown to be effective com...

2010 31 citations

Publication Info

Year: 2011
Type: article
Volume: 20
Issue: 1
Pages: 14-22
Citations: 1732
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Acoustic Modeling Using Deep Belief Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1732

OpenAlex

Cite This

APA Style

                            
                                    Abdelrahman Mohamed, 
                                
                                    George E. Dahl, 
                                
                                    Geoffrey E. Hinton
                                
                            (2011). 
                            Acoustic Modeling Using Deep Belief Networks. 
                            IEEE Transactions on Audio Speech and Language Processing
                            , 20
                            (1)
                            , 14-22.
                            https://doi.org/10.1109/tasl.2011.2109382

Identifiers

DOI: 10.1109/tasl.2011.2109382