Global optimization of a neural network-hidden Markov model hybrid

Abstract

The integration of multilayered and recurrent artificial neural networks (ANNs) with hidden Markov models (HMMs) is addressed. ANNs are suitable for approximating functions that compute new acoustic parameters, whereas HMMs have been proven successful at modeling the temporal structure of the speech signal. In the approach described, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech database are reported.

Keywords

Computer scienceArtificial neural networkHidden Markov modelArtificial intelligenceMarkov modelMarkov chainMachine learning

Affiliated Institutions

Related Publications

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

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

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

Speech Recognition Using Augmented Conditional Random Fields

Yasser Hifny , Steve Renals

Acoustic modeling based on hidden Markov models (HMMs) is employed by state-of-the-art stochastic speech recognition systems. Although HMMs are a natural choice to warp the time...

2009 IEEE Transactions on Audio Speech and... 82 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: 1992
Type: article
Volume: 3
Issue: 2
Pages: 252-259
Citations: 200
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Global optimization of a neural network-hidden Markov model hybrid

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

200

OpenAlex

Cite This

APA Style

                            
                                
                                    Yoshua Bengio, 
                                
                                    Renato De Mori, 
                                
                                    Giovanni Flammia
                                
                                et al.
                            
                            (1992). 
                            Global optimization of a neural network-hidden Markov model hybrid. 
                            IEEE Transactions on Neural Networks
                            , 3
                            (2)
                            , 252-259.
                            https://doi.org/10.1109/72.125866
                        

Identifiers

DOI: 10.1109/72.125866