Global optimization of a neural network-hidden Markov model hybrid

Abstract

An original method for integrating artificial neural networks (ANN) with hidden Markov models (HMM) is proposed. ANNs are suitable for performing phonetic classification, 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.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

Keywords

Hidden Markov modelTIMITArtificial neural networkComputer scienceSpeech recognitionArtificial intelligenceSequence (biology)Markov modelPattern recognition (psychology)SIGNAL (programming language)Markov chainMachine learning

Affiliated Institutions

McGill University CA

Related Publications

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

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

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

Reception of multiple co-channel digital signals using antenna arrays with applications to PCS

Shilpa Talwar , A. Paulraj , Mats Viberg

Antenna arrays can be used to increase system capacity in PCS networks by supporting multiple co-channel users per cell in receive and in transmit. We propose a novel approach f...

2002 11 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: 2002
Type: article
Volume: ii
Pages: 789-794
Citations: 18
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

OpenAlex

Cite This

APA Style

                            
                                    Yoshua Bengio, 
                                
                                    Renato De Mori, 
                                
                                    Giovanni Flammia
                                
                                et al.
                            
                            (2002). 
                            Global optimization of a neural network-hidden Markov model hybrid. 
                            
                            , ii
                            
                            , 789-794.
                            https://doi.org/10.1109/ijcnn.1991.155435

Identifiers

DOI: 10.1109/ijcnn.1991.155435