Evaluation of 2-way Iraqi Arabic–English speech translation systems using automated metrics

The Defense Advanced Research Projects Agency (DARPA) Spoken Language Communication and Translation System for Tactical Use (TRANSTAC) program (http://1.usa.gov/transtac) faced many challenges in applying automated measures of translation quality to Iraqi Arabic–English speech translation dialogues. Features of speech data in general and of Iraqi Arabic data in particular undermine basic assumptions of automated measures that depend on matching system outputs to reference translations. These features are described along with the challenges they present for evaluating machine translation quality using automated metrics. We show that scores for translation into Iraqi Arabic exhibit higher correlations with human judgments when they are computed from normalized system outputs and reference translations. Orthographic normalization, lexical normalization, and operations involving light stemming resulted in higher correlations with human judgments.     

Optimal design and verification of temporal and spatial filters using second-order cone programming approach

11 Introduction The filters are widely used in many applications of signal processing. Filter design is an important research problem in many diverse application areas. The filters we usually refer to are temporal filters, which pass the frequency components of interest and attenuate the others. A spatial filter passes the signal radiating from a specific location and attenuates signals from other locations. Beamformer that widely used in radar, sonar,and wireless communications is a kind of …     

Analysis of multibody systems with flexible plates using variational graph-theoretic methods

This work treats the problem of modelling multibody systems with structural flexibility. By combining linear graph theory with the principle of virtual work and finite elements, a dynamic formulation is obtained that extends graph-theoretic (GT) modelling methods to the analysis of thin flexible plates for multibody systems. The system is represented by a linear graph, in which nodes represent reference frames on flexible plates, and edges represent components that connect these frames. To generate the equations of motion with elastic deformations, the flexible plates are discretized using a triangular thin shell finite element based on the discrete Kirchhoff criterion and can be used to discretize bidirectional bodies such as satellite panels, flatbed trailers, and mechanisms with plates. Three flexible systems with plates are analyzed to illustrate the performance of this new variational graph-theoretic formulation and its ability to generate directly a set of motion equations for flexible multibody systems (FMS) without additional user input.     

Application of prosody models for developing speech systems in Indian languages

In this paper we demonstrate the use of prosody models for developing speech systems in Indian languages. Duration and intonation models developed using feedforward neural networks are considered as prosody models. Labelled broadcast news data in the languages Hindi, Telugu, Tamil and Kannada is used for developing the neural network models for predicting the duration and intonation. The features representing the positional, contextual and phonological constraints are used for developing the prosody models. In this paper, the use of prosody models is illustrated using speech recognition, speech synthesis, speaker recognition and language identification applications. Autoassociative neural networks and support vector machines are used as classification models for developing the speech systems. The performance of the speech systems has shown to be improved by combining the prosodic features along with one popular spectral feature set consisting of Weighted Linear Prediction Cepstral Coefficients (WLPCCs).     

Recognition of control chart patterns using multi-resolution wavelets analysis and neural networks☆

Control charts pattern recognition is one of the most important tools in statistical process control to identify process problems. Unnatural patterns exhibited by such charts can be associated with certain assignable causes affecting the process. In this paper, multi-resolution wavelets analysis (MRWA) is used to extract distinct features for unnatural patterns by providing distinct time–frequency coefficients. A reduced set of parameters is derived from these coefficients and used as input to an artificial neural network (ANN) classifier. Results show that the performance of the proposed technique in classifying shift, trend and cyclic patterns is superior to that of ANN classifier, which operated on coded observed data.     

Evaluation of Face Datasets as Tools for Assessing the Performance of Face Recognition Methods

Face datasets are considered a primary tool for evaluating the efficacy of face recognition methods. Here we show that in many of the commonly used face datasets, face images can be recognized accurately at a rate significantly higher than random even when no face, hair or clothes features appear in the image. The experiments were done by cutting a small background area from each face image, so that each face dataset provided a new image dataset which included only seemingly blank images. Then, an image classification method was used in order to check the classification accuracy. Experimental results show that the classification accuracy ranged between 13.5% (color FERET) to 99% (YaleB). These results indicate that the performance of face recognition methods measured using face image datasets may be biased. Compilable source code used for this experiment is freely available for download via the Internet.     

Computationally efficient solutions for tracking people with a mobile robot: an experimental evaluation of Bayesian filters

Modern service robots will soon become an essential part of modern society. As they have to move and act in human environments, it is essential for them to be provided with a fast and reliable tracking system that localizes people in the neighborhood. It is therefore important to select the most appropriate filter to estimate the position of these persons. This paper presents three efficient implementations of multisensor-human tracking based on different Bayesian estimators: Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF) and Sampling Importance Resampling (SIR) particle filter. The system implemented on a mobile robot is explained, introducing the methods used to detect and estimate the position of multiple people. Then, the solutions based on the three filters are discussed in detail. Several real experiments are conducted to evaluate their performance, which is compared in terms of accuracy, robustness and execution time of the estimation. The results show that a solution based on the UKF can perform as good as particle filters and can be often a better choice when computational efficiency is a key issue.     

Analysis of Multi-Sort Algorithm on Multi-Mesh of Trees (MMT) architecture

Various sorting algorithms using parallel architectures have been proposed in the search for more efficient results. This paper introduces the Multi-Sort Algorithm for Multi-Mesh of Trees (MMT) Architecture for N=n ⁴ elements with more efficient time complexity compared to previous architectures. The shear sort algorithm on Single Instruction Multiple Data (SIMD) mesh model requires \(4\sqrt{N}+O\sqrt{N}\) time for sorting N elements, arranged on a \(\sqrt{N}\times \sqrt{N}\) mesh, whereas Multi-Sort algorithm on the SIMD Multi-Mesh (MM) Architecture takes O(N ^1/4) time for sorting the same N elements, which proves that Multi-Sort is a better sorting approach. We have improved the time complexity of intrablock Sort. The Communication time complexity for 2D Sort in MM is O(n), whereas this time in MMT is O(log?n). The time complexity of compare–exchange step in MMT is same as that in MM, i.e., O(n). It has been found that the time complexity of the Multi-Sort on MMT has been improved as on Multi-Mesh architecture.     

Spectral necessary and sufficient conditions for sampling-period-independent stabilisation of periodic and aperiodic sampled-data systems using a class of generalised sampled-data hold functions

Sampling-period-independent (SPI) stabilisation of both periodic and aperiodic sampled-data systems using a class of generalised sampled-data hold functions is addressed. It is proved that for this specific class of hold functions, a continuous-time linear system with rank-minimal input matrix and with non-defective eigenvalues on the imaginary axis is SPI-stabilisable if and only if the spectrum of the system is contained in the closed left-half plane. A systematic procedure for constructing suitable state-feedback controllers is also provided. Several examples are finally discussed for illustration.     

Elimination of noise on transcranial Doppler signal using IIR filters designed with artificial bee colony – ABC-algorithm

Biomedical signals are usually contaminated by noise generated from sources such as power line interference and disturbances produced by the movement of the recording electrodes. Also the signal-to-noise ratio of biomedical signals is usually quite low. In addition, biomedical signals often interfere with each other. Therefore, the filters employed for eliminating noise and interference are significant in the medical practice. Digital infinite impulse response (IIR) filters have shorter filter length than the finite impulse response (FIR) filters with the same frequency characteristic. Therefore, in this work, an approach based on digital IIR filters are described for the elimination of noise on transcranial Doppler by using artificial bee colony (ABC) which is a popular swarm based optimization algorithm introduced recently. Moreover, the performance of the proposed approach is compared to particle swarm optimization algorithm.     

LP spectra vs. Mel spectra for identification of professional mimics in Indian languages

Automatic Speaker Recognition (ASR) is an economic tool for voice biometrics because of availability of low cost and powerful processors. For an ASR system to be successful in practical environments, it must have high mimic resistance, i.e., the system should not be defeated by determined mimics which may be either identical twins or professional mimics. In this paper, we demonstrate the effectiveness of Linear Prediction (LP)-based features, viz., Linear Prediction Coefficients (LPC) and Linear Prediction Cepstral Coefficients (LPCC) over filterbank-based features such as Mel-Frequency Cepstral Coefficients (MFCC) and newly proposed Teager energy-based MFCC (T-MFCC) for the identification of professional mimics in Indian languages. Results are reported for real and fictitious experiments. On the whole, it is observed that LP-based features perform better than filterbank-based features (an average jump of 23.21% and 31.43% for fictitious experiments with professional mimic in Marathi and Hindi, respectively, whereas there is an average jump of 1.64% for real experiments with professional mimic in Hindi) and we believe that this is the first time such results on identification of professional mimics in ASR are obtained. Analysis of the results is given with the help of Mean Square Error (MSE) between training and testing utterances for mimic’s imitations for target speakers and target speakers’ normal voice. Fourier spectra and corresponding LP spectra for target speaker and its impersonations provided by professional mimic are shown to justify the results. Finally, dependence of LPC on physiological characteristics of vocal tract and its relation with respect to the problem addressed in this paper is studied.     

Robust fitting of implicitly defined surfaces using Gauss–Newton-type techniques

We describe Gauss–Newton-type methods for fitting implicitly defined curves and surfaces to given unorganized data points. The methods are suitable not only for least-squares approximation, but they can also deal with general error functions, such as approximations to the ℓ ₁ or ℓ _∞ norm of the vector of residuals. Two different definitions of the residuals will be discussed, which lead to two different classes of methods: direct methods and data-based ones. In addition we discuss the continuous versions of the methods, which furnish geometric interpretations as evolution processes. It is shown that the data-based methods—which are less costly, as they work without the computation of the closest points—can efficiently deal with error functions that are adapted to noisy and uncertain data. In addition, we observe that the interpretation as evolution process allows to deal with the issues of regularization and with additional constraints.

Structural analysis of the intervertebral discs adjacent to an interbody fusion using multibody dynamics and finite element cosimulation

This work describes a methodology for the dynamic and structural analysis of complex (bio)mechanical systems that joins both multibody dynamics and finite element domains, in a synergetic way, through a cosimulation procedure that takes benefit of the advantages of each numerical formulation. To accomplish this goal, a cosimulation module is developed based on the gluing algorithm X-X, which is the key element responsible for the management of the information flux between the two software packages (each using its own mathematical formulation and code). The X-X algorithm uses for each cosimulated structure multiple pairs of reference points whose kinematics are solved by the multibody module and prescribed, as initial data, to the finite element counterpart. The finite element module, by its turn, solves the structural problem imposed by the prescribed kinematics, calculates the resulting generalized loads applied over the reference points and return these loads back to the multibody module that uses them to solve the dynamic problem and to calculate new reference kinematics to prescribe to the finite element module in the next time step. The proposed method is applied to study the cervical spine dynamics in a pathologic situation in which an intersomatic fusion is simulated to confirm its potential advantages. Taking into account the proposed simulation scenario, a cervical spine multibody model that includes the rigid vertebrae, the facet joints’ and spinous processes’ contacts, ligaments and the finite element models of the intervertebral discs, and their surrogates is developed. The proposed model is simulated for extension in a forward dynamics perspective.     

Replication of sub-100 nm structures using h- and s-PDMS composite stamps

Soft-UV-NIL as replication technique was used to replicate sub-100 nm structures. The aim of this work is the stamp production and the replication of structures with dimensions smaller than 100 nm in a simple manner. Composite stamps composed of two layers, a thin hard PDMS layer supported by a thick soft PDMS (s-PDMS) layer are compared to common s-PDMS stamps regarding the resolution by using a Siemens star (star burst pattern) as test structure. The master is fabricated by electron beam lithography in a 140 nm thick PMMA resist layer. The stamp is molded directly from the structured resist, without any additional anti sticking treatment. Therefore the resist thickness determines the aspect ratio, which is 1.5 at the resolution limit. The replication is done in a UV-curing cycloaliphatic epoxy material. The employed test structure provides good comparability, the resolution limit at a glance, and it integrates a smooth transition from micro- to nanostructures. Therefore it is a capable structure to characterize the UV-NIL.     

Log-Linear Convergence and Divergence of the Scale-Invariant (1+1)-ES in Noisy Environments

Noise is present in many real-world continuous optimization problems. Stochastic search algorithms such as Evolution Strategies (ESs) have been proposed as effective search methods in such contexts. In this paper, we provide a mathematical analysis of the convergence of a (1+1)-ES on unimodal spherical objective functions in the presence of noise. We prove for a multiplicative noise model that for a positive expected value of the noisy objective function, convergence or divergence happens depending on the infimum of the support of the noise. Moreover, we investigate convergence rates and show that log-linear convergence is preserved in presence of noise. This result is a strong theoretical foundation of the robustness of ESs with respect to noise.     

Design and realization of a high resolution (640 × 480) SWIR image acquisition system

A new image acquisition system module for extracting signals of high-resolution short wave infrared (SWIR) from a focal plane array (FPA) is presented in this study. The short wave infrared (SWIR—with wavelength about 900–1,700 nm) images have been proven its unique values in many applications such as military, semiconductor inspection and aviation security. The designs for the SWIR data acquisition system module consists of digitization and acquisition of FPA signals, design of synchronous dynamic random access memory controller and real-time image signal transformation and display. Three major steps involved towards a successful SWIR module—(1) Selection of hardware ICs according to specification for the FPA; (2) Design of a timing generator for the image acquisition system to control FPA and other ICs by Verilog HDL programming; (3) Integrate the individual modules on a PCB. The SWIR image output signals are successfully generated in the format of National Television System Committee (NSTC), which can be displayed on a common NTSC monitor, flat panel displays with an AV input terminal or a CRT display in a favorable speed of frame rate at 30 per second.     

Analysis of kinematics/statics and workspace of a 2(SP+SPR+SPU) serial–parallel manipulator

The kinematics/statics and workspace of a 2(SP+SPR+SPU) serial–parallel manipulator are studied systematically. First, a 2(SP+SPR+SPU) manipulator including an upper and a lower SP+SPR+SPU parallel manipulators is constructed, and the inverse/forward displacements, velocity, acceleration and statics of the lower/upper parallel manipulators are studied, respectively. Second, the kinematics and statics of the lower/upper manipulators are combined and the displacement, velocity, acceleration, statics, and workspace of a 2(SP+SPR+SPU) manipulator are analyzed systematically. Third, the analytic solutions’ examples are given and verified by the simulation mechanism. This manipulator has some potential applications for the robot’s arm, leg, and twist, the serial–parallel machine tools, the sensor, the surgical manipulator, the tunnel borer, the barbette of warship, and the satellite surveillance platform.