Search results for: part of speech
1879 Architecture of Speech-based Registration System
Authors: Mayank Kumar, D B Mahesh Kumar, Ashwin S Kumar, N K Srinath
Abstract:
In this era of technology, fueled by the pervasive usage of the internet, security is a prime concern. The number of new attacks by the so-called “bots", which are automated programs, is increasing at an alarming rate. They are most likely to attack online registration systems. Technology, called “CAPTCHA" (Completely Automated Public Turing test to tell Computers and Humans Apart) do exist, which can differentiate between automated programs and humans and prevent replay attacks. Traditionally CAPTCHA-s have been implemented with the challenge involved in recognizing textual images and reproducing the same. We propose an approach where the visual challenge has to be read out from which randomly selected keywords are used to verify the correctness of spoken text and in turn detect the presence of human. This is supplemented with a speaker recognition system which can identify the speaker also. Thus, this framework fulfills both the objectives – it can determine whether the user is a human or not and if it is a human, it can verify its identity.
Keywords: CAPTCHA, automatic speech recognition, keyword spotting.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15391878 Automatic Lip Contour Tracking and Visual Character Recognition for Computerized Lip Reading
Authors: Harshit Mehrotra, Gaurav Agrawal, M.C. Srivastava
Abstract:
Computerized lip reading has been one of the most actively researched areas of computer vision in recent past because of its crime fighting potential and invariance to acoustic environment. However, several factors like fast speech, bad pronunciation, poor illumination, movement of face, moustaches and beards make lip reading difficult. In present work, we propose a solution for automatic lip contour tracking and recognizing letters of English language spoken by speakers using the information available from lip movements. Level set method is used for tracking lip contour using a contour velocity model and a feature vector of lip movements is then obtained. Character recognition is performed using modified k nearest neighbor algorithm which assigns more weight to nearer neighbors. The proposed system has been found to have accuracy of 73.3% for character recognition with speaker lip movements as the only input and without using any speech recognition system in parallel. The approach used in this work is found to significantly solve the purpose of lip reading when size of database is small.Keywords: Contour Velocity Model, Lip Contour Tracking, LipReading, Visual Character Recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23921877 Studies of Zooplankton in Gdańsk Basin (2010-2011)
Authors: Dzierzbicka-Glowacka, A. Lemieszek, M. Figiela
Abstract:
In 2010-2011, the research on zooplankton was conducted in the southern part of the Baltic Sea to determine seasonal variability in changes occurring throughout the zooplankton in 2010 and 2011, both in the region of Gdańsk Deep, and in the western part of Gdańsk Bay. The research in the sea showed that the taxonomic composition of holoplankton in the southern part of the Baltic Sea was similar to that recorded in this region for many years. The maximum values of abundance and biomass of zooplankton both in the Deep and the Bay of Gdańsk were observed in the summer season. Copepoda dominated in the composition of zooplankton for almost the entire study period, while rotifers occurred in larger numbers only in the summer 2010 in the Gdańsk Deep as well as in May and July 2010 in the western part of Gdańsk Bay, and meroplankton – in April 2011.
Keywords: Baltic Sea, composition, Gdańsk Bay, zooplankton.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 34691876 Study on Bending Characteristics of Square Tube Using Energy Absorption Part
Authors: Shigeyuki Haruyama, Zefry Darmawan, Ken Kaminishi
Abstract:
In the square tube subjected to the bending load, the rigidity of the entire square tube is reduced when a collapse occurs due to local stress concentration. Therefore, in this research, the influence of bending load on the square tube with attached energy absorbing part was examined and reported. The analysis was conducted by using Finite Element Method (FEM) to produced bending deflection and buckling points. Energy absorption was compared from rigidity of attached part and square tube body. Buckling point was influenced by the rigidity of attached part and the thickness rate of square tube.
Keywords: Square tube, bending stress, energy absorption, finite element analysis, rigidity.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13481875 Intelligent Design of Reconfigurable Machines
Authors: Majid Tolouei-Rad
Abstract:
This paper presents methodologies for developing an intelligent CAD system assisting in analysis and design of reconfigurable special machines. It describes a procedure for determining feasibility of utilizing these machines for a given part and presents a model for developing an intelligent CAD system. The system analyzes geometrical and topological information of the given part to determine possibility of the part being produced by reconfigurable special machines from a technical point of view. Also feasibility of the process from a economical point of view is analyzed. Then the system determines proper positioning of the part considering details of machining features and operations needed. This involves determination of operation types, cutting tools and the number of working stations needed. Upon completion of this stage the overall layout of the machine and machining equipment required are determined.Keywords: CAD, Knowledge based system, Reconfigurable
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14141874 Neuro-Fuzzy Based Model for Phrase Level Emotion Understanding
Authors: Vadivel Ayyasamy
Abstract:
The present approach deals with the identification of Emotions and classification of Emotional patterns at Phrase-level with respect to Positive and Negative Orientation. The proposed approach considers emotion triggered terms, its co-occurrence terms and also associated sentences for recognizing emotions. The proposed approach uses Part of Speech Tagging and Emotion Actifiers for classification. Here sentence patterns are broken into phrases and Neuro-Fuzzy model is used to classify which results in 16 patterns of emotional phrases. Suitable intensities are assigned for capturing the degree of emotion contents that exist in semantics of patterns. These emotional phrases are assigned weights which supports in deciding the Positive and Negative Orientation of emotions. The approach uses web documents for experimental purpose and the proposed classification approach performs well and achieves good F-Scores.
Keywords: Emotions, sentences, phrases, classification, patterns, fuzzy, positive orientation, negative orientation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 10671873 An Adaptive Approach to Synchronization of Two Chua's Circuits
Authors: Majid Reza Naseh, Mohammad Haeri
Abstract:
This paper introduces an adaptive control scheme to synchronize two identical Chua's systems. Introductory part of the paper is presented in the first part of the paper and then in the second part, a new theorem is proposed based on which an adaptive control scheme is developed to synchronize two identical modified Chua's circuit. Finally, numerical simulations are included to verify the effectiveness of the proposed control method.
Keywords: Chaos synchronization, adaptive control, Chua's circuits.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14251872 Intelligent Speaker Verification based Biometric System for Electronic Commerce Applications
Authors: Anastasis Kounoudes, Stephanos Mavromoustakos
Abstract:
Electronic commerce is growing rapidly with on-line sales already heading for hundreds of billion dollars per year. Due to the huge amount of money transferred everyday, an increased security level is required. In this work we present the architecture of an intelligent speaker verification system, which is able to accurately verify the registered users of an e-commerce service using only their voices as an input. According to the proposed architecture, a transaction-based e-commerce application should be complemented by a biometric server where customer-s unique set of speech models (voiceprint) is stored. The verification procedure requests from the user to pronounce a personalized sequence of digits and after capturing speech and extracting voice features at the client side are sent back to the biometric server. The biometric server uses pattern recognition to decide whether the received features match the stored voiceprint of the customer who claims to be, and accordingly grants verification. The proposed architecture can provide e-commerce applications with a higher degree of certainty regarding the identity of a customer, and prevent impostors to execute fraudulent transactions.Keywords: Speaker Recognition, Biometrics, E-commercesecurity.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17251871 The Use of Process-Oriented Methods of Calculation to Determine the Costs of Logistics Processes
Authors: Tomas Cechura, Michal Simon
Abstract:
The aim of this paper is to create a proposal for determining the costs of logistics processes by using process-oriented calculation methods. The traditional approach is that logistics costs are part of manufacturing overhead which is usually calculated as a percentage surcharge. Therefore in the traditional approach it is not obvious where and in which activities costs were incurred. So it is impossible to trace logistics costs to products. Our point of view is trying to fix or at least improve this issue. Another benefit of applying the process approach is identification of logistics processes which are otherwise part of manufacturing overhead. In the first part this paper describes the development of process-oriented methods over time. The next part shows the possibility of implementing the process-oriented method called Prozesskostenrechnung to logistics processes. The conclusion summarizes advantages and disadvantages of using this method in logistics.
Keywords: Cost, logistics, calculation, process-oriented method.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15801870 Efficient High Fidelity Signal Reconstruction Based on Level Crossing Sampling
Authors: Negar Riazifar, Nigel G. Stocks
Abstract:
This paper proposes strategies in level crossing (LC) sampling and reconstruction that provide high fidelity signal reconstruction for speech signals; these strategies circumvent the problem of exponentially increasing number of samples as the bit-depth is increased and hence are highly efficient. Specifically, the results indicate that the distribution of the intervals between samples is one of the key factors in the quality of signal reconstruction; including samples with short intervals does not improve the accuracy of the signal reconstruction, whilst samples with large intervals lead to numerical instability. The proposed sampling method, termed reduced conventional level crossing (RCLC) sampling, exploits redundancy between samples to improve the efficiency of the sampling without compromising performance. A reconstruction technique is also proposed that enhances the numerical stability through linear interpolation of samples separated by large intervals. Interpolation is demonstrated to improve the accuracy of the signal reconstruction in addition to the numerical stability. We further demonstrate that the RCLC and interpolation methods can give useful levels of signal recovery even if the average sampling rate is less than the Nyquist rate.
Keywords: Level crossing sampling, numerical stability, speech processing, trigonometric polynomial.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4091869 The Experience with SiC MOSFET and Buck Converter Snubber Design
Authors: P. Vaculik
Abstract:
The newest semiconductor devices on the market are MOSFET transistors based on the silicon carbide – SiC. This material has exclusive features thanks to which it becomes a better switch than Si – silicon semiconductor switch. There are some special features that need to be understood to enable the device’s use to its full potential. The advantages and differences of SiC MOSFETs in comparison with Si IGBT transistors have been described in first part of this article. Second part describes driver for SiC MOSFET transistor and last part of article represents SiC MOSFET in the application of buck converter (step-down) and design of simple RC snubber.
Keywords: SiC, Si, MOSFET, IGBT, SBD, RC snubber.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 55681868 Improved Closed Set Text-Independent Speaker Identification by Combining MFCC with Evidence from Flipped Filter Banks
Authors: Sandipan Chakroborty, Anindya Roy, Goutam Saha
Abstract:
A state of the art Speaker Identification (SI) system requires a robust feature extraction unit followed by a speaker modeling scheme for generalized representation of these features. Over the years, Mel-Frequency Cepstral Coefficients (MFCC) modeled on the human auditory system has been used as a standard acoustic feature set for SI applications. However, due to the structure of its filter bank, it captures vocal tract characteristics more effectively in the lower frequency regions. This paper proposes a new set of features using a complementary filter bank structure which improves distinguishability of speaker specific cues present in the higher frequency zone. Unlike high level features that are difficult to extract, the proposed feature set involves little computational burden during the extraction process. When combined with MFCC via a parallel implementation of speaker models, the proposed feature set outperforms baseline MFCC significantly. This proposition is validated by experiments conducted on two different kinds of public databases namely YOHO (microphone speech) and POLYCOST (telephone speech) with Gaussian Mixture Models (GMM) as a Classifier for various model orders.
Keywords: Complementary Information, Filter Bank, GMM, IMFCC, MFCC, Speaker Identification, Speaker Recognition.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22681867 Automatic Building an Extensive Arabic FA Terms Dictionary
Authors: El-Sayed Atlam, Masao Fuketa, Kazuhiro Morita, Jun-ichi Aoe
Abstract:
Field Association (FA) terms are a limited set of discriminating terms that give us the knowledge to identify document fields which are effective in document classification, similar file retrieval and passage retrieval. But the problem lies in the lack of an effective method to extract automatically relevant Arabic FA Terms to build a comprehensive dictionary. Moreover, all previous studies are based on FA terms in English and Japanese, and the extension of FA terms to other language such Arabic could be definitely strengthen further researches. This paper presents a new method to extract, Arabic FA Terms from domain-specific corpora using part-of-speech (POS) pattern rules and corpora comparison. Experimental evaluation is carried out for 14 different fields using 251 MB of domain-specific corpora obtained from Arabic Wikipedia dumps and Alhyah news selected average of 2,825 FA Terms (single and compound) per field. From the experimental results, recall and precision are 84% and 79% respectively. Therefore, this method selects higher number of relevant Arabic FA Terms at high precision and recall.
Keywords: Arabic Field Association Terms, information extraction, document classification, information retrieval.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17231866 Multi Switched Split Vector Quantizer
Authors: M. Satya Sai Ram, P. Siddaiah, M. Madhavi Latha
Abstract:
Vector quantization is a powerful tool for speech coding applications. This paper deals with LPC Coding of speech signals which uses a new technique called Multi Switched Split Vector Quantization, This is a hybrid of two product code vector quantization techniques namely the Multi stage vector quantization technique, and Switched split vector quantization technique,. Multi Switched Split Vector Quantization technique quantizes the linear predictive coefficients in terms of line spectral frequencies. From results it is proved that Multi Switched Split Vector Quantization provides better trade off between bitrate and spectral distortion performance, computational complexity and memory requirements when compared to Switched Split Vector Quantization, Multi stage vector quantization, and Split Vector Quantization techniques. By employing the switching technique at each stage of the vector quantizer the spectral distortion, computational complexity and memory requirements were greatly reduced. Spectral distortion was measured in dB, Computational complexity was measured in floating point operations (flops), and memory requirements was measured in (floats).Keywords: Unconstrained vector quantization, Linear predictiveCoding, Split vector quantization, Multi stage vector quantization, Switched Split vector quantization, Line Spectral Frequencies.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17301865 A Study of Recycle Materials to Develop for Auto Part
Authors: Sittichai Kaewkuekool, Vanchai Laemlaksakul
Abstract:
At the present, auto part industries have become higher challenge in strategy market. As this consequence, manufacturers need to have better response to customers in terms of quality, cost, and delivery time. Moreover, they need to have a good management in factory to comply with international standard maximum capacity and lower cost. This would lead companies to have to order standard part from aboard and become the major cost of inventory. The development of auto part research by recycling materials experiment is to compare the auto parts from recycle materials to international auto parts (CKD). Factors studied in this research were the recycle material ratios of PU-foam, felt, and fabric. Results of recycling materials were considered in terms of qualities and properties on the parameters such as weight, sound absorption, water absorption, tensile strength, elongation, and heat resistance with the CKD. The results were showed that recycling materials would be used to replace for the CKD.
Keywords: International auto parts, recycling materials.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20551864 Bose-Einstein Condensation in Neutral Many Bosonic System
Authors: M. Al-Sugheir, M. Sakhreya, G. Alna'washi, F. Al-Dweri
Abstract:
In this work, the condensation fraction and transition temperature of neutral many bosonic system are studied within the static fluctuation approximation (SFA). The effect of the potential parameters such as the strength and range on the condensate fraction was investigated. A model potential consisting of a repulsive step potential and an attractive potential well was used. As the potential strength or the core radius of the repulsive part increases, the condensation fraction is found to be decreased at the same temperature. Also, as the potential depth or the range of the attractive part increases, the condensation fraction is found to be increased. The transition temperature is decreased as the potential strength or the core radius of the repulsive part increases, and it increases as the potential depth or the range of the attractive part increases.Keywords: About four key words or phrases in alphabetical order, separated by commas
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 11981863 Solving Part Type Selection and Loading Problem in Flexible Manufacturing System Using Real Coded Genetic Algorithms – Part II: Optimization
Authors: Wayan F. Mahmudy, Romeo M. Marian, Lee H. S. Luong
Abstract:
This paper presents modeling and optimization of two NP-hard problems in flexible manufacturing system (FMS), part type selection problem and loading problem. Due to the complexity and extent of the problems, the paper was split into two parts. The first part of the papers has discussed the modeling of the problems and showed how the real coded genetic algorithms (RCGA) can be applied to solve the problems. This second part discusses the effectiveness of the RCGA which uses an array of real numbers as chromosome representation. The novel proposed chromosome representation produces only feasible solutions which minimize a computational time needed by GA to push its population toward feasible search space or repair infeasible chromosomes. The proposed RCGA improves the FMS performance by considering two objectives, maximizing system throughput and maintaining the balance of the system (minimizing system unbalance). The resulted objective values are compared to the optimum values produced by branch-and-bound method. The experiments show that the proposed RCGA could reach near optimum solutions in a reasonable amount of time.
Keywords: Flexible manufacturing system, production planning, part type selection problem, loading problem, real-coded genetic algorithm
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19621862 Understanding the Silence: When Courts Don-t Speak About Religion
Authors: Kalindi Kokal
Abstract:
India recognizes the personal laws of the various religious communities that reside in the country. At the same time all the institutions of the state in India are committed to the value of secularism. This paper has been developed on the basis of a case study that indicates the dynamics of religion in the working of the lower judiciary in India. Majority of the commentary on religion and the judiciary has focused on debates surrounding the existence and application of personal laws. This paper, through a case study in the lower judiciary, makes an attempt to examine whether the interface between religion and the judiciary goes beyond personal laws. The first part of this paper explains the history and application of personal laws in social, political and legal contexts in India. The second part examines the case study located in two courts of first instance, following into the third part which provides an analysis of the empirical evidence. The fourth part focuses on preliminary observations about why there is a hesitancy to speak about religion in relation to the working of the judicial system.Keywords: Lower Courts, India, Legal Pluralism, Personal Law.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14781861 Study on Energy Absorption Characteristic of Cab Frame with FEM
Authors: Shigeyuki Haruyama, Oke Oktavianty, Zefry Darmawan, Tadayuki Kyoutani, Ken Kaminishi
Abstract:
Cab’s frame strength is considered as an important factor in excavator’s operator safety, especially during roll-over. In this study, we use a model of cab frame with different thicknesses and perform elastoplastic numerical analysis by using Finite Element Method (FEM). Deformation mode and energy absorption's of cab’s frame part are investigated on two conditions, with wrinkle and without wrinkle. The occurrence of wrinkle when deforming cab frame can reduce energy absorption, and among 4 parts with wrinkle, the energy absorption significantly decreases in part C. Residual stress that generated upon the bending process of part C is analyzed to confirm it possibility in increasing the energy absorption.
Keywords: ROPS, FEM, hydraulic excavator, cab frame, energy absorption.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15321860 Comparison among Various Question Generations for Decision Tree Based State Tying in Persian Language
Authors: Nasibeh Nasiri, Dawood Talebi Khanmiri
Abstract:
Performance of any continuous speech recognition system is highly dependent on performance of the acoustic models. Generally, development of the robust spoken language technology relies on the availability of large amounts of data. Common way to cope with little data for training each state of Markov models is treebased state tying. This tying method applies contextual questions to tie states. Manual procedure for question generation suffers from human errors and is time consuming. Various automatically generated questions are used to construct decision tree. There are three approaches to generate questions to construct HMMs based on decision tree. One approach is based on misrecognized phonemes, another approach basically uses feature table and the other is based on state distributions corresponding to context-independent subword units. In this paper, all these methods of automatic question generation are applied to the decision tree on FARSDAT corpus in Persian language and their results are compared with those of manually generated questions. The results show that automatically generated questions yield much better results and can replace manually generated questions in Persian language.
Keywords: Decision Tree, Markov Models, Speech Recognition, State Tying.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17121859 Impact of Process Parameters on Tensile Strength of Fused Deposition Modeling Printed Crisscross Poylactic Acid
Authors: Shilpesh R. Rajpurohit, Harshit K. Dave
Abstract:
Additive manufacturing gains the popularity in recent times, due to its capability to create prototype as well functional as end use product directly from CAD data without any specific requirement of tooling. Fused deposition modeling (FDM) is one of the widely used additive manufacturing techniques that are used to create functional end use part of polymer that is comparable with the injection-molded parts. FDM printed part has an application in various fields such as automobile, aerospace, medical, electronic, etc. However, application of FDM part is greatly affected by poor mechanical properties. Proper selection of the process parameter could enhance the mechanical performance of the printed part. In the present study, experimental investigation has been carried out to study the behavior of the mechanical performance of the printed part with respect to process variables. Three process variables viz. raster angle, raster width and layer height have been varied to understand its effect on tensile strength. Further, effect of process variables on fractured surface has been also investigated.
Keywords: 3D printing, fused deposition modeling, layer height, raster angle, raster width, tensile strength.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16471858 Fenugreek in the Ecological Areas of Belarus and France
Authors: Elena Fauquet-Alekhine-Pavlovskaya, Irina M. Nesterova
Abstract:
On the territory of France fenugreek is spread since long on a line from the Gironde to the Italian border. In Belarus experimental cultivation has begun since 2004. Experiments with fenugreek variety Ovari 4 were conducted about time of sowing in order to study their growth, development, and evaluation of productivity in the North-east part of Belarus and Central part of France. Reaching full ripeness of seeds the plants of fenugreek in the Central part of France requires about 94-97 days. Average seeds yield of 2011-2012 is 1259 kg/ha. Plant height is about 36,8 cm. Plants were affected by aphid and in the high moist agro-climatic conditions by powdery mildew. In North-east part of Belarus plants need 86-93 days to full ripeness. Plants of fenugreek have steam about 59 cm. The average seeds yield of 2007-2009 was about 723 kg/ha. Plants were resistant to aphid and diseases.
Keywords: Fenugreek, time of sowing, variety, yield.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 26821857 Fundamental Problems in the Operation of the Automotive Parts Industry Small and Medium Businesses in Bangkok and Surrounding Provinces
Authors: P. Thepnarintra
Abstract:
The purposes of this study were to: 1) investigate operation conditions of SME automotive part industry in Bangkok and vicinity and 2) to compare operation problem levels of SME automotive part industry in Bangkok and vicinity according to the sizes of the enterprises. Samples in this study included 196 entrepreneurs of SME automotive part industry in Bangkok and vicinity derived from simple random sampling and calculation from R. V. Krejcie and D. W. Morgan’s tables. Research statistics included frequency, percentage, mean, standard deviation, and T-test. The results revealed that in general the problem levels of SME automotive part industry in Bangkok and vicinity were high. When considering in details, it was found that the problem levels were high at every aspect, i.e. personal, production, export, finance, and marketing respectively. The comparison of the problem levels according to the sizes of the enterprises revealed statistically significant differences at .05. When considering on each aspect, it was found that the aspect with the statistical difference at .05 included 5 aspects, i.e. production, marketing, finance, personal, and export. The findings also showed that small enterprises faced more severe problems than those of medium enterprises.Keywords: Automotive part industry, operation problems, SME, perimeter.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15831856 Evaluation of Features Extraction Algorithms for a Real-Time Isolated Word Recognition System
Authors: Tomyslav Sledevič, Artūras Serackis, Gintautas Tamulevičius, Dalius Navakauskas
Abstract:
Paper presents an comparative evaluation of features extraction algorithm for a real-time isolated word recognition system based on FPGA. The Mel-frequency cepstral, linear frequency cepstral, linear predictive and their cepstral coefficients were implemented in hardware/software design. The proposed system was investigated in speaker dependent mode for 100 different Lithuanian words. The robustness of features extraction algorithms was tested recognizing the speech records at different signal to noise rates. The experiments on clean records show highest accuracy for Mel-frequency cepstral and linear frequency cepstral coefficients. For records with 15 dB signal to noise rate the linear predictive cepstral coefficients gives best result. The hard and soft part of the system is clocked on 50 MHz and 100 MHz accordingly. For the classification purpose the pipelined dynamic time warping core was implemented. The proposed word recognition system satisfy the real-time requirements and is suitable for applications in embedded systems.
Keywords: Isolated word recognition, features extraction, MFCC, LFCC, LPCC, LPC, FPGA, DTW.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 35281855 Tibyan Automated Arabic Correction Using Machine-Learning in Detecting Syntactical Mistakes
Authors: Ashwag O. Maghraby, Nida N. Khan, Hosnia A. Ahmed, Ghufran N. Brohi, Hind F. Assouli, Jawaher S. Melibari
Abstract:
The Arabic language is one of the most important languages. Learning it is so important for many people around the world because of its religious and economic importance and the real challenge lies in practicing it without grammatical or syntactical mistakes. This research focused on detecting and correcting the syntactic mistakes of Arabic syntax according to their position in the sentence and focused on two of the main syntactical rules in Arabic: Dual and Plural. It analyzes each sentence in the text, using Stanford CoreNLP morphological analyzer and machine-learning approach in order to detect the syntactical mistakes and then correct it. A prototype of the proposed system was implemented and evaluated. It uses support vector machine (SVM) algorithm to detect Arabic grammatical errors and correct them using the rule-based approach. The prototype system has a far accuracy 81%. In general, it shows a set of useful grammatical suggestions that the user may forget about while writing due to lack of familiarity with grammar or as a result of the speed of writing such as alerting the user when using a plural term to indicate one person.
Keywords: Arabic Language acquisition and learning, natural language processing, morphological analyzer, part-of-speech.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 10221854 A New Color Image Database for Benchmarking of Automatic Face Detection and Human Skin Segmentation Techniques
Authors: Abdallah S. Abdallah, Mohamad A bou El-Nasr, A. Lynn Abbott
Abstract:
This paper presents a new color face image database for benchmarking of automatic face detection algorithms and human skin segmentation techniques. It is named the VT-AAST image database, and is divided into four parts. Part one is a set of 286 color photographs that include a total of 1027 faces in the original format given by our digital cameras, offering a wide range of difference in orientation, pose, environment, illumination, facial expression and race. Part two contains the same set in a different file format. The third part is a set of corresponding image files that contain human colored skin regions resulting from a manual segmentation procedure. The fourth part of the database has the same regions converted into grayscale. The database is available on-line for noncommercial use. In this paper, descriptions of the database development, organization, format as well as information needed for benchmarking of algorithms are depicted in detail.Keywords: Image database, color image analysis, facedetection, skin segmentation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25751853 Opinion Mining Framework in the Education Domain
Authors: A. M. H. Elyasir, K. S. M. Anbananthen
Abstract:
The internet is growing larger and becoming the most popular platform for the people to share their opinion in different interests. We choose the education domain specifically comparing some Malaysian universities against each other. This comparison produces benchmark based on different criteria shared by the online users in various online resources including Twitter, Facebook and web pages. The comparison is accomplished using opinion mining framework to extract, process the unstructured text and classify the result to positive, negative or neutral (polarity). Hence, we divide our framework to three main stages; opinion collection (extraction), unstructured text processing and polarity classification. The extraction stage includes web crawling, HTML parsing, Sentence segmentation for punctuation classification, Part of Speech (POS) tagging, the second stage processes the unstructured text with stemming and stop words removal and finally prepare the raw text for classification using Named Entity Recognition (NER). Last phase is to classify the polarity and present overall result for the comparison among the Malaysian universities. The final result is useful for those who are interested to study in Malaysia, in which our final output declares clear winners based on the public opinions all over the web.
Keywords: Entity Recognition, Education Domain, Opinion Mining, Unstructured Text.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 29551852 Active Learning in Computer Exercises on Electronics
Authors: Zoja Raud, Valery Vodovozov
Abstract:
Modelling and simulation provide effective way to acquire engineering experience. An active approach to modelling and simulation proposed in the paper involves, beside the compulsory part directed by the traditional step-by-step instructions, the new optional part basing on the human’s habits to design thus stimulating the efforts towards success in active learning. Computer exercises as a part of engineering curriculum incorporate a set of effective activities. In addition to the knowledge acquired in theoretical training, the described educational arrangement helps to develop problem solutions, computation skills, and experimentation performance along with enhancement of practical experience and qualification.
Keywords: Modelling, simulation, engineering education, electronics, active learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23601851 Hand Gesture Interpretation Using Sensing Glove Integrated with Machine Learning Algorithms
Authors: Aqsa Ali, Aleem Mushtaq, Attaullah Memon, Monna
Abstract:
In this paper, we present a low cost design for a smart glove that can perform sign language recognition to assist the speech impaired people. Specifically, we have designed and developed an Assistive Hand Gesture Interpreter that recognizes hand movements relevant to the American Sign Language (ASL) and translates them into text for display on a Thin-Film-Transistor Liquid Crystal Display (TFT LCD) screen as well as synthetic speech. Linear Bayes Classifiers and Multilayer Neural Networks have been used to classify 11 feature vectors obtained from the sensors on the glove into one of the 27 ASL alphabets and a predefined gesture for space. Three types of features are used; bending using six bend sensors, orientation in three dimensions using accelerometers and contacts at vital points using contact sensors. To gauge the performance of the presented design, the training database was prepared using five volunteers. The accuracy of the current version on the prepared dataset was found to be up to 99.3% for target user. The solution combines electronics, e-textile technology, sensor technology, embedded system and machine learning techniques to build a low cost wearable glove that is scrupulous, elegant and portable.Keywords: American sign language, assistive hand gesture interpreter, human-machine interface, machine learning, sensing glove.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27181850 A Novel Web Metric for the Evaluation of Internet Trends
Authors: Radek Malinský, Ivan Jelínek
Abstract:
Web 2.0 (social networking, blogging and online forums) can serve as a data source for social science research because it contains vast amount of information from many different users. The volume of that information has been growing at a very high rate and becoming a network of heterogeneous data; this makes things difficult to find and is therefore not almost useful. We have proposed a novel theoretical model for gathering and processing data from Web 2.0, which would reflect semantic content of web pages in better way. This article deals with the analysis part of the model and its usage for content analysis of blogs. The introductory part of the article describes methodology for the gathering and processing data from blogs. The next part of the article is focused on the evaluation and content analysis of blogs, which write about specific trend.Keywords: Blog, Sentiment Analysis, Web 2.0, Webometrics
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3532