Sparse Multilayer Perceptron for Phoneme Recognition

Sivaram, G.S.V.S.; Heřmanský, Hynek

doi:10.1109/tasl.2011.2129510

Cited by 54 publications

(33 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(3) Feed-forward deep networks. It is composed of the multiple encoder layer overlay, such as the multilayer perceptron [38][39]. Convolution neural network (CNN) is the first successful training multi-layer network structure learning algorithm as based on reconstruction error of input and output energy function through the forward and back propagation network connection weights of process optimization and adjustment made to minimize the overall energy function.…”

Section: The Modified Deep Convolution Neural Networkmentioning

confidence: 99%

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Huang¹,

Zhang²

2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

show abstract

Section: The Modified Deep Convolution Neural Networkmentioning

confidence: 99%

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Huang¹,

Zhang²

2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

show abstract

“…In the other approach, the output from DNNs are used as input to conventional GMM-HMMs. The former is called the hybrid approach [14,19,20], and the latter is called the tandem approach [21][22][23]. In this paper, we adopt the hybrid approach, which has a simple structure and therefore is easy to build.…”

Section: Dnn-hmmmentioning

confidence: 99%

Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature

Mimura

Sakai

Kawahara

2015

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

We propose an approach to reverberant speech recognition adopting deep learning in the front-end as well as back-end of a reverberant speech recognition system, and a novel method to improve the dereverberation performance of the front-end network using phone-class information. At the front-end, we adopt a deep autoencoder (DAE) for enhancing the speech feature parameters, and speech recognition is performed in the back-end using DNN-HMM acoustic models trained on multi-condition data. The system was evaluated through the ASR task in the Reverb Challenge 2014. The DNN-HMM system trained on the multi-condition training set achieved a conspicuously higher word accuracy compared to the MLLR-adapted GMM-HMM system trained on the same data. Furthermore, feature enhancement with the deep autoencoder contributed to the improvement of recognition accuracy especially in the more adverse conditions. While the mapping between reverberant and clean speech in DAE-based dereverberation is conventionally conducted only with the acoustic information, we presume the mapping is also dependent on the phone information. Therefore, we propose a new scheme (pDAE), which augments a phone-class feature to the standard acoustic features as input. Two types of the phone-class feature are investigated. One is the hard recognition result of monophones, and the other is a soft representation derived from the posterior outputs of monophone DNN. The augmented feature in either type results in a significant improvement (7-8 % relative) from the standard DAE.

show abstract

“…Compared with traditional machine learning algorithms, the research results are particularly remarkable in speech recognition and image processing. For example, Deng et al [2] and Sivaram et al [3] successfully applied deep learning technology to address phone recognition problems; Yu et al [4] and Dahl et al [5] used deep neural networks in large vocabulary speech recognition, and the results are satisfactory; In Large Scale Visual Recognition Challenge 2012 competition, Krizhevsky established a large-scale convolution neural network (CNN) with 60,000,000 weights and 650,000 neurons, which trained 1.2 million high-resolution image data. Those images contain 1000 different species, and the results on 50,000 testing images show that the proposed deep learning method greatly reduces recognition errors for high-resolution images [6].…”

Section: Introductionmentioning

confidence: 99%

Text classification based on deep belief network and softmax regression

Jiang

Liang

Feng

et al. 2016

Neural Comput & Applic

229

103

View full text Add to dashboard Cite

In this paper, we propose a novel hybrid text classification model based on deep belief network and softmax regression. To solve the sparse high-dimensional matrix computation problem of texts data, a deep belief network is introduced. After the feature extraction with DBN, softmax regression is employed to classify the text in the learned feature space. In pre-training procedures, the deep belief network and softmax regression are first trained, respectively. Then, in the fine-tuning stage, they are transformed into a coherent whole and the system parameters are optimized with Limited-memory BroydenFletcher-Goldfarb-Shanno algorithm. The experimental results on Reuters-21,578 and 20-Newsgroup corpus show that the proposed model can converge at fine-tuning stage and perform significantly better than the classical algorithms, such as SVM and KNN.

show abstract

Sparse Multilayer Perceptron for Phoneme Recognition

Cited by 54 publications

References 32 publications

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature

Text classification based on deep belief network and softmax regression

Contact Info

Product

Resources

About