scholarly journals Neural networks used for speech recognition

2010 ◽  
Vol 20 (1) ◽  
pp. 1-7 ◽  
Author(s):  
Wouter Gevaert ◽  
Georgi Tsenov ◽  
Valeri Mladenov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Speech Recognition ◽  
Radial Basis Functions ◽  
Back Propagation ◽  
Classification Performance ◽  
Basis Functions ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
Propagation Algorithm

In this paper is presented an investigation of the speech recognition classification performance. This investigation on the speech recognition classification performance is performed using two standard neural networks structures as the classifier. The utilized standard neural network types include Feed-forward Neural Network (NN) with back propagation algorithm and a Radial Basis Functions Neural Networks.

scholarly journals Modeling of Speech Recognition Using Artificial Neural Network

2019 ◽  
Vol 8 (9) ◽  
pp. 1225-1229
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Pattern Matching ◽  
Back Propagation ◽  
Experimental Result ◽  
Communication Link ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
The Voice

Automatic speech recognition has attained a lot of significance as it can act as easy communication link between machines and humans. This mode of communication is easy for man to use as it is effortless and easy. Many approaches for extraction of the features of the speech and classification of speech have been considered. This paper unveils the importance of neutral network and the way it can be used for recognition of speech. Mel Frequency Cepstrum Coefficients is made use of for extraction of the features from the voice. For pattern matching neural network has been used. MATLAB has been used to show how the speech is recognized. In this paper the speech recognition has been done firstly by multilayer feed forward neural network using Back propagation algorithm. Then the process of speech recognition is shown by using Radial basis function neural network. The paper then analyzes the performance of both the algorithms and experimental result shows that BPNN outperforms the RBFNN.

scholarly journals Building robust neural networks using different loss functions

2021 ◽  
pp. 67-82
Author(s):  
Maria Sivak ◽  
◽  
Vladimir Timofeev ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Loss Function ◽  
Back Propagation ◽  
Loss Functions ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Propagation Algorithm ◽  
Error Back Propagation Algorithm ◽  
Parameter Values

The paper considers the problem of building robust neural networks using different robust loss functions. Applying such neural networks is reasonably when working with noisy data, and it can serve as an alternative to data preprocessing and to making neural network architecture more complex. In order to work adequately, the error back-propagation algorithm requires a loss function to be continuously or two-times differentiable. According to this requirement, two five robust loss functions were chosen (Andrews, Welsch, Huber, Ramsey and Fair). Using the above-mentioned functions in the error back-propagation algorithm instead of the quadratic one allows obtaining an entirely new class of neural networks. For investigating the properties of the built networks a number of computational experiments were carried out. Different values of outliers’ fraction and various numbers of epochs were considered. The first step included adjusting the obtained neural networks, which lead to choosing such values of internal loss function parameters that resulted in achieving the highest accuracy of a neural network. To determine the ranges of parameter values, a preliminary study was pursued. The results of the first stage allowed giving recommendations on choosing the best parameter values for each of the loss functions under study. The second stage dealt with comparing the investigated robust networks with each other and with the classical one. The analysis of the results shows that using the robust technique leads to a significant increase in neural network accuracy and in a learning rate.

Artificial Neural Network Modelling for Waste

2011 ◽  
pp. 224-263 ◽  
Author(s):  
Eldon R. Rene ◽  
M. Estefanía López ◽  
María C. Veiga ◽  
Christian Kennes
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Wastewater Treatment ◽  
Back Propagation ◽  
Back Propagation Algorithm ◽  
Network Modelling ◽  
Waste Gas ◽  
Propagation Algorithm ◽  
Artificial Neural

Due to their inherent robustness, artificial neural network models have proven to be successful and have been used extensively in biological wastewater treatment applications. However, only recently, with the scientific advancements made in biological waste gas treatment systems, the application of neural networks have slowly gained the practical momentum for performance monitoring in this field. Simple neural models, after vigorous training and testing, are able to generalize the results of a wide range of operating conditions, with high prediction accuracy. This chapter gives a fundamental insight and overview of the process mechanism of different biological waste gas (biofilters, biotrickling filters, continuous stirred tank bioreactors and monolith bioreactors), and wastewater treatment systems (activated sludge process, trickling filter and sequencing batch reactors). The basic theory of artificial neural networks is explained with a clear understanding of the back propagation algorithm. A generalized neural network modelling procedure for waste treatment applications is outlined, and the role of back propagation algorithm network parameters is discussed. Anew, the application of neural networks for solving specific environmental problems is presented in the form of a literature review.

Application of a Multi-Structure Neural Network (MSNN) to Sorting Pistachio Nuts

1997 ◽  
Vol 08 (01) ◽  
pp. 55-61 ◽  
Author(s):  
Ahmad Ghazanfari ◽  
Anthony Kusalik ◽  
Joseph Irudayaraj
Keyword(s):  
Neural Network ◽  
Single Neuron ◽  
Back Propagation ◽  
Classification Performance ◽  
Fourier Descriptor ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
Pistachio Nuts ◽  
The Individual

A multi-structure neural network (MSNN) classifier consisting of four discriminators followed by a maximum selector was designed and applied to classification of four grades of pistachio nuts. Each discriminator was a multi-layer feed-forward neural network with two hidden layers and a single-neuron output layer. Fourier descriptor of the nuts' boundaries and their area were used as the recognition features. The individual discriminators were trained using a biased technique and a back-propagation algorithm. The MSNN classifier gave an average classification performance of 95.0%. This was an increase of 14.8% over the performance of a multi-layer neural network (MLNN) with similar complexity for classifying the same set of patterns.

scholarly journals Temporal solar irradiance variability analysis using neural networks

2015 ◽  
Vol 11 (S320) ◽  
pp. 333-338
Author(s):  
Ambelu Tebabal ◽  
Baylie Damtie ◽  
Melessew Nigussie
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Solar Irradiance ◽  
Dominant Role ◽  
Back Propagation ◽  
Total Solar Irradiance ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
Surface Magnetism ◽  
Feed Forward

AbstractA feed-forward neural network which can account for nonlinear relationship was used to model total solar irradiance (TSI). A single layer feed-forward neural network with Levenberg-marquardt back-propagation algorithm have been implemented for modeling daily total solar irradiance from daily photometric sunspot index, and core-to-wing ratio of Mg II index data. In order to obtain the optimum neural network for TSI modeling, the root mean square error (RMSE) and mean absolute error (MAE) have been taken into account. The modeled and measured TSI have the correlation coefficient of about R=0.97. The neural networks (NNs) model output indicates that reconstructed TSI from solar proxies (photometric sunspot index and Mg II) can explain 94% of the variance of TSI. This modeled TSI using NNs further strengthens the view that surface magnetism indeed plays a dominant role in modulating solar irradiance.

scholarly journals Relationship between isoseismal area and magnitude of historical earthquakes in Greece by a hybrid fuzzy neural network method

2012 ◽  
Vol 12 (1) ◽  
pp. 37-45 ◽  
Author(s):  
G-A. Tselentis ◽  
E. Sokos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Back Propagation ◽  
Target Function ◽  
Historical Earthquakes ◽  
Strong Nonlinearity ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
Artificial Neural

Abstract. In this paper we suggest the use of diffusion-neural-networks, (neural networks with intrinsic fuzzy logic abilities) to assess the relationship between isoseismal area and earthquake magnitude for the region of Greece. It is of particular importance to study historical earthquakes for which we often have macroseismic information in the form of isoseisms but it is statistically incomplete to assess magnitudes from an isoseismal area or to train conventional artificial neural networks for magnitude estimation. Fuzzy relationships are developed and used to train a feed forward neural network with a back propagation algorithm to obtain the final relationships. Seismic intensity data from 24 earthquakes in Greece have been used. Special attention is being paid to the incompleteness and contradictory patterns in scanty historical earthquake records. The results show that the proposed processing model is very effective, better than applying classical artificial neural networks since the magnitude macroseismic intensity target function has a strong nonlinearity and in most cases the macroseismic datasets are very small.

Sign in / Sign up

Export Citation Format

Share Document