Deep Belief Networks using discriminative features for phone recognition

Abstract

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 features that capture the higher-order statistical structure of the data. These features can be used to initialize the hidden units of a feed-forward neural network that is then trained to predict the HMM state for the central frame of the window. Initializing with features that are good at generating speech makes the neural network perform much better than initializing with random weights. DBNs have already been used successfully for phone recognition with input coefficients that are MFCCs or filterbank outputs. In this paper, we demonstrate that they work even better when their inputs are speaker adaptive, discriminative features. On the standard TIMIT corpus, they give phone error rates of 19.6% using monophone HMMs and a bigram language model and 19.4% using monophone HMMs and a trigram language model.

Keywords

Discriminative modelComputer scienceArtificial intelligencePattern recognition (psychology)PhoneSpeech recognitionDeep belief networkDeep learning

Affiliated Institutions

IBM (United States) US

Related Publications

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

Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR

Oriol Vinyals , Suman Ravuri

In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of...

2011 55 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

A Fast Learning Algorithm for Deep Belief Nets

Geoffrey E. Hinton , Simon Osindero , Yee‐Whye Teh

We show how to use “complementary priors” to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. U...

2006 Neural Computation 16027 citations

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

Ali Sharif Razavian , Hossein Azizpour , Josephine Sullivan +1 more

Recent results indicate that the generic descriptors ex-tracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is i...

2014 4279 citations

Publication Info

Year: 2011
Type: article
Pages: 5060-5063
Citations: 289
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Deep Belief Networks using discriminative features for phone recognition

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

289

OpenAlex

Cite This

APA Style

                            
                                    Abdelrahman Mohamed, 
                                
                                    Tara N. Sainath, 
                                
                                    George E. Dahl
                                
                                et al.
                            
                            (2011). 
                            Deep Belief Networks using discriminative features for phone recognition. 
                            
                            , 5060-5063.
                            https://doi.org/10.1109/icassp.2011.5947494

Identifiers

DOI: 10.1109/icassp.2011.5947494