Implicit excitation source features for robust language identification

In present work, the robustness of excitation source features has been analyzed for language identification (LID) task. The raw samples of linear prediction (LP) residual signal, its magnitude and phase components are processed at sub-segmental, segmental and supra-segmental levels for capturing the robust language-specific phonotactic information. Present LID study has been carried out on 27 Indian languages from Indian Institute of Technology Kharagpur-Multi Lingual Indian Language Speech Corpus (IITKGP-MLILSC). Gaussian mixture models are used to develop the LID systems using robust language-specific excitation source information. Robustness of excitation source information has been evinced in view of (i) background noise, (ii) varying amount of training data and (iii) varying length of test samples. Finally, the robustness of proposed excitation source features is compared with the well-known spectral features using LID performances obtained from IITKGP-MLILSC database. Segmental level excitation source features obtained from raw samples of LP residual signal and its phase component perform better at low SNR levels, compared with the vocal tract features.     

Combining the evidences of temporal and spectral enhancement techniques for improving the performance of Indian language identification system in the presence of background noise

Language Identification has gained significant importance in recent years, both in research and commercial market place, demanding an improvement in the ability of machines to distinguish between languages. Although methods like Gaussian mixture models, hidden Markov models and neural networks are used for identifying languages the problem of language identification in noisy environments could not be addressed so far. This paper addresses the performance of automatic language identification system in noisy environments. A comparative performance analysis of speech enhancement techniques like minimum mean squared estimation, spectral subtraction and temporal processing, with different types of noise at different SNRs, is presented here. Though these individual enhancement techniques may not yield good performance with different types of noise at different SNRs, it is proposed to combine the evidences of all these techniques to improve the overall performance of the system significantly. The language identification studies are performed using IITKGP-MLILSC (IIT Kharagpur-Multilingual Indian Language Speech Corpus) databases which consists of 27 languages.     

GMM based language identification system using robust features

In this work, we have proposed new feature vectors for spoken language identification (LID) system. The Mel frequency cepstral coefficients (MFCC) and formant frequencies derived using short-time window speech signal. Formant frequencies are extracted from linear prediction (LP) analysis of speech signal. Using these two kind of features of speech signal, new feature vectors are derived using cluster based computation. A GMM based classifier has been designed using these new feature vectors. The language specific apriori knowledge is applied on the recognition output. The experiments are carried out on OGI database and LID recognition performance is improved.     

A hierarchical language identification system for Indian languages

Automatic spoken Language IDentification (LID) is the task of identifying the language from a short duration of speech signal uttered by an unknown speaker. In this work, an attempt has been made to develop a two level language identification system for Indian languages using acoustic features. In the first level, the system identifies the family of the spoken language, and then it is fed to the second level which aims at identifying the particular language in the corresponding family. The performance of the system is analyzed for various acoustic features and different classifiers. The suitable acoustic feature and the pattern classification model are suggested for effective identification of Indian languages. The system has been modeled using hidden Markov model (HMM), Gaussian mixture model (GMM) and artificial neural networks (ANN). We studied the discriminative power of the system for the features mel frequency cepstral coefficients (MFCC), MFCC with delta and acceleration coefficients and shifted delta cepstral (SDC) coefficients. Then the LID performance as a function of the different training and testing set sizes has been studied. To carry out the experiments, a new database has been created for 9 Indian languages. It is shown that GMM based LID system using MFCC with delta and acceleration coefficients is performing well with 80.56% accuracy. The performance of GMM based LID system with SDC is also considerable.     

Dynamical system parameter identification using deep recurrent cell networks

Neural Computing and Applications - In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear...     

Combining belief networks and neural networks for scenesegmentation

We are concerned with the problem of image segmentation, in which each pixel is assigned to one of a predefined finite number of labels. In Bayesian image analysis, this requires fusing together local predictions for the class labels with a prior model of label images. Following the work of Bouman and Shapiro (1994), we consider the use of tree-structured belief networks (TSBNs) as prior models. The parameters in the TSBN are trained using a maximum-likelihood objective function with the EM algorithm and the resulting model is evaluated by calculating how efficiently it codes label images. A number of authors have used Gaussian mixture models to connect the label field to the image data. We compare this approach to the scaled-likelihood method of Smyth (1994) and Morgan and Bourlard (1995), where local predictions of pixel classification from neural networks are fused with the TSBN prior. Our results show a higher performance is obtained with the neural networks. We evaluate the classification results obtained and emphasize not only the maximum a posteriori segmentation, but also the uncertainty, as evidenced e.g., by the pixelwise posterior marginal entropies. We also investigate the use of conditional maximum-likelihood training for the TSBN and find that this gives rise to improved classification performance over the ML-trained TSBN     

Learning images using compositional pattern-producing neural networks for source camera identification and digital demographic diagnosis

In this work, we propose a neural network based framework to explore the statistical correlation intrinsically embedded due to interpolations in a relatively small neighborhood, in which the interpolation process is cognized from the interpolation results and the spatially invariant stylized computational rules in interpolation algorithms are simulated and learned by adjusting weights and bias values of neural networks. Experiments show that, our approach is competitive among the state of the art of source camera identification methods. It is also effective for digital forgery detection and other interesting experiments such as the digital demographic diagnosis and prediction. The framework can also be applied to other types of image interpolations such as super-resolution.     

Nonlinear dynamic system identification using Chebyshev functionallink artificial neural networks

A computationally efficient artificial neural network (ANN) for the purpose of dynamic nonlinear system identification is proposed. The major drawback of feedforward neural networks, such as multilayer perceptrons (MLPs) trained with the backpropagation (BP) algorithm, is that they require a large amount of computation for learning. We propose a single-layer functional-link ANN (FLANN) in which the need for a hidden layer is eliminated by expanding the input pattern by Chebyshev polynomials. The novelty of this network is that it requires much less computation than that of a MLP. We have shown its effectiveness in the problem of nonlinear dynamic system identification. In the presence of additive Gaussian noise, the performance of the proposed network is found to be similar or superior to that of a MLP. A performance comparison in terms of computational complexity has also been carried out.     

Nonlinear system identification using memetic differential evolution trained neural networks

Several gradient-based approaches such as back propagation (BP) and Levenberg Marquardt (LM) methods have been developed for training the neural network (NN) based systems. But, for multimodal cost functions these procedures may lead to local minima, therefore, the evolutionary algorithms (EAs) based procedures are considered as promising alternatives. In this paper we focus on a memetic algorithm based approach for training the multilayer perceptron NN applied to nonlinear system identification. The proposed memetic algorithm is an alternative to gradient search methods, such as back-propagation and back-propagation with momentum which has inherent limitations of many local optima. Here we have proposed the identification of a nonlinear system using memetic differential evolution (DE) algorithm and compared the results with other six algorithms such as Back-propagation (BP), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), Genetic Algorithm Back-propagation (GABP), Particle Swarm Optimization combined with Back-propagation (PSOBP). In the proposed system identification scheme, we have exploited DE to be hybridized with the back propagation algorithm, i.e. differential evolution back-propagation (DEBP) where the local search BP algorithm is used as an operator to DE. These algorithms have been tested on a standard benchmark problem for nonlinear system identification to prove their efficacy. First examples shows the comparison of different algorithms which proves that the proposed DEBP is having better identification capability in comparison to other. In example 2 good behavior of the identification method is tested on an one degree of freedom (1DOF) experimental aerodynamic test rig, a twin rotor multi-input-multi-output system (TRMS), finally it is applied to Box and Jenkins Gas furnace benchmark identification problem and its efficacy has been tested through correlation analysis.     

Graph attention-based collaborative filtering for user-specific recommender system using knowledge graph and deep neural networks

Knowledge and Information Systems - Collaborative filtering suffers from the issues of data sparsity and cold start. Due to which recommendation models that only rely on the user–item...     

Multilayer dynamic neural networks for non-linear system on-line identification

To identify on-line a quite general class of non-linear systems, this paper proposes a new stable learning law of the multilayer dynamic neural networks. A Lyapunov-like analysis is used to derive this stable learning procedure for the hidden layer as well as for the output layer. An algebraic Riccati equation is considered to construct a bound for the identification error. The suggested learning algorithm is similar to the well-known backpropagation rule of the multilayer perceptrons but with an additional term which assure the stability property of the identification error.     

Combining models from neural networks and inductive learning algorithms

The knowledge-based artificial neural network (KBANN) is composed of phases involving the expression of domain knowledge, the abstraction of domain knowledge at neural networks, the training of neural networks, and finally, the extraction of rules from trained neural networks. The KBANN attempts to open up the neural network black box and generates symbolic rules with (approximately) the same predictive power as the neural network itself. An advantage of using KBANN is that the neural network considers the contribution of the inputs towards classification as a group, while rule-based algorithms like C5.0 measure the individual contribution of the inputs one at a time as the tree is grown. The knowledge consolidation model (KCM) combines the rules extracted using KBANN (NeuroRule), frequency matrix (which is similar to the Naïve Bayesian technique), and C5.0 algorithm. The KCM can effectively integrate multiple rule sets into one centralized knowledge base. The cumulative rules from other single models can improve overall performance as it can reduce error-term and increase R-square. The key idea in the KCM is to combine a number of classifiers such that the resulting combined system achieves higher classification accuracy and efficiency than the original single classifiers. The aim of KCM is to design a composite system that outperforms any individual classifier by pooling together the decisions of all classifiers. Another advantage of KCM is that it does not need the memory space to store the dataset as only extracted knowledge is necessary in build this integrated model. It can also reduce the costs from storage allocation, memory, and time schedule. In order to verify the feasibility and effectiveness of KCM, personal credit rating dataset provided by a local bank in Seoul, Republic of Korea is used in this study. The results from the tests show that the performance of KCM is superior to that of the other single models such as multiple discriminant analysis, logistic regression, frequency matrix, neural networks, decision trees, and NeuroRule. Moreover, our model is superior to a previous algorithm for the extraction of rules from general neural networks.     

Detection of novel coronavirus from chest X-rays using deep convolutional neural networks

Multimedia Tools and Applications - With over 172 Million people infected with the novel coronavirus (COVID-19) globally and with the numbers increasing exponentially, the dire need of a fast...     

Combining expert neural networks using reinforcement feedback for learning primitive grasping behavior

This paper present an architecture for combining a mixture of experts. The architecture has two unique features: 1) it assumes no prior knowledge of the size or structure of the mixture and allows the number of experts to dynamically expand during training, and 2) reinforcement feedback is used to guide the combining/expansion operation. The architecture is particularly suitable for applications when there is a need to approximate a many-to-many mapping. An example of such a problem is the task of training a robot to grasp arbitrarily shaped objects. This task requires the approximation of a many-to-many mapping, since various configurations can be used to grasp an object, and several objects can share the same grasping configuration. Experiments in a simulated environment using a 28-object database showed how the algorithm dynamically combined and expanded a mixture of neural networks to achieve the learning task. The paper also presents a comparison with two other nonlearning approaches.     

Dynamic neural networks with hybrid structures for nonlinear system identification

Dynamic neural networks (DNNs) have important properties that make them convenient to be used together with nonlinear control approaches based on state space models and differential geometry, such as feedback linearisation. However the mapping capability of DNNs are quite limited due to their fixed structure, that is, the number of layers and the number of hidden units. An example shown in this paper has demonstrated this limitation of DNNs. The development of novel DNN structures, which has good mapping capability, is a relevant challenge being addressed in this paper. Although the structure is changed minorly only, the mapping capability of the new designed DNN in this paper has been improved dramatically. Previous work [J. Deng et al., 2005. The dynamic neural network of a hybrid structure for nonlinear system identification. In: 16th IFAC World Congress, Prague.] presents a new dynamic neural network structure which is suitable for the identification of highly nonlinear systems, which needs the outputs from the real system for training and operation. This paper presents a hybrid dynamic neural network structure which presents a similar idea of serial–parallel hybrid structure, but it uses an output from another neural network for training and operation classified as a serial–parallel model. This type of DNNs does not require the output of the plant to be used as an input to the model. This neural network has the advantages of good mapping capabilities and flexibilities in training complicated systems, compared to the existed DNNs. A theoretical proof showing how this hybrid dynamic neural network can approximate finite trajectories of general nonlinear dynamic systems is given. To illustrate the capabilities of the new structure, neural networks are trained to identify a real nonlinear 3D crane system.     

Prediction and identification using wavelet-based recurrent fuzzy neural networks

This paper presents a wavelet-based recurrent fuzzy neural network (WRFNN) for prediction and identification of nonlinear dynamic systems. The proposed WRFNN model combines the traditional Takagi-Sugeno-Kang (TSK) fuzzy model and the wavelet neural networks (WNN). This paper adopts the nonorthogonal and compactly supported functions as wavelet neural network bases. Temporal relations embedded in the network are caused by adding some feedback connections representing the memory units into the second layer of the feedforward wavelet-based fuzzy neural networks (WFNN). An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the degree measure to obtain the number of fuzzy rules and wavelet functions. Meanwhile, the parameter learning is based on the gradient descent method for adjusting the shape of the membership function and the connection weights of WNN. Finally, computer simulations have demonstrated that the proposed WRFNN model requires fewer adjustable parameters and obtains a smaller rms error than other methods.     

of overparametrization in non-linear system identification and neural networks

The effects of overparametrization in non-linear system identification and neural networks are often presented as overfitting to a particular data set. An overparametrized model tends to interpolate the data set and can fail to capture the underlying dynamics represented by the data. Past studies have usually concentrated on overparametrisation in the number of model terms or the number of hidden layer nodes. In the present study, the effects of several forms of overparametrization on the model dynamics are compared using qualitative validation methods. The dynamic properties of the identified model or the trained network are graphically displayed and compared with those of the real system. It is shown that overparametrization in the number of time lags or input nodes has the worst effect on the dynamic properties of the resulting model.     

Fine-tuning deep convolutional neural networks for distinguishing illustrations from photographs

Systems for aggregating illustrations require a function for automatically distinguishing illustrations from photographs as they crawl the network to collect images. A previous attempt to implement this functionality by designing basic features that were deemed useful for classification achieved an accuracy of only about 58%. On the other hand, deep neural networks had been successful in computer vision tasks, and convolutional neural networks (CNNs) had performed good at extracting such useful image features automatically. We evaluated alternative methods to implement this classification functionality with focus on deep neural networks. As the result of experiments, the method that fine-tuned deep convolutional neural network (DCNN) acquired 96.8% accuracy, outperforming the other models including the custom CNN models that were trained from scratch. We conclude that DCNN with fine-tuning is the best method for implementing a function for automatically distinguishing illustrations from photographs.     

Fuzzy neural networks for intelligent design retrieval using associative manufacturing features

In the conceptual design stage, designers usually initiate a design concept through an association activity. The activity helps designers collect and retrieve reference information regarding a current design subject instead of starting from scratch. By modifying previous designs, designers can create a new design in a much shorter time. To computerize this process, this paper proposes an intelligent design retrieval system involving soft computing techniques for both feature and object association functions. A feature association method that utilizes fuzzy relation and fuzzy composition is developed to increase the searching spectrum. In the mean time, object association functions composed by a fuzzy neural network allow designers to control the similarity of retrieved designs. Our implementation result shows that the intelligent design retrieval system with two soft computing based association functions can retrieve target reference designs as expected.