Search results for: handwritten word recognition

Authors: Meruyert Serik, Nassipzhan Duisegaliyeva, Danara Tleumagambetova, Madina Ermaganbetova

Abstract:

This research paper explores the process of creating a proctoring system by evaluating the implementation of practical face recognition algorithms. Students of educational programs reviewed the research work "6B01511-Computer Science", "7M01511-Computer Science", "7M01525- STEM Education," and "8D01511-Computer Science" of Eurasian National University named after L.N. Gumilyov. As an outcome, a proctoring system will be created, enabling the conduction of tests and ensuring academic integrity checks within the system. Due to the correct operation of the system, test works are carried out. The result of the creation of the proctoring system will be the basis for the automation of the informational, educational portal developed by machine learning.

Keywords: artificial intelligence, education portal, face recognition, machine learning, proctoring

Procedia PDF Downloads 127

Authors: Assel Jaxylykova, Alexnder Pak

Abstract:

This study utilized a Self-Organizing Map (SOM) for unsupervised learning on the CONLL-2003 dataset for Named Entity Recognition (NER). The process involved encoding words into 300-dimensional vectors using FastText. These vectors were input into a SOM grid, where training adjusted node weights to minimize distances. The SOM provided a topological representation for identifying and clustering named entities, demonstrating its efficacy without labeled examples. Results showed an F1-measure of 0.86, highlighting SOM's viability. Although some methods achieve higher F1 measures, SOM eliminates the need for labeled data, offering a scalable and efficient alternative. The SOM's ability to uncover hidden patterns provides insights that could enhance existing supervised methods. Further investigation into potential limitations and optimization strategies is suggested to maximize benefits.

Keywords: named entity recognition, natural language processing, self-organizing map, CONLL-2003, semantics

Procedia PDF Downloads 50

Authors: Ali Cheraghian, Farshid Hajati, Soheila Gheisari, Yongsheng Gao

Abstract:

In this paper, we present a novel 2.5D face recognition method based on Gabor Discrete Cosine Transform (GDCT). In the proposed method, the Gabor filter is applied to extract feature vectors from the texture and the depth information. Then, Discrete Cosine Transform (DCT) is used for dimensionality and redundancy reduction to improve computational efficiency. The system is combined texture and depth information in the decision level, which presents higher performance compared to methods, which use texture and depth information, separately. The proposed algorithm is examined on publically available Bosphorus database including models with pose variation. The experimental results show that the proposed method has a higher performance compared to the benchmark.

Keywords: Gabor filter, discrete cosine transform, 2.5d face recognition, pose

Procedia PDF Downloads 328

Authors: Heng Yang, Tao Luo, Yakun Zhang, Kai Wang, Wei Qin, Liang Xie, Ye Yan, Erwei Yin

Abstract:

Recent years have seen that audio-visual recognition has shown great potential in a strong noise environment. The existing method of audio-visual recognition has explored methods with ResNet and feature fusion. However, on the one hand, ResNet always occupies a large amount of memory resources, restricting the application in engineering. On the other hand, the feature merging also brings some interferences in a high noise environment. In order to solve the problems, we proposed an effective framework with bidirectional distillation. At first, in consideration of the good performance in extracting of features, we chose the light model, Efficientnet as our extractor of spatial features. Secondly, self-distillation was applied to learn more information from raw data. Finally, we proposed a bidirectional distillation in decision-level fusion. In more detail, our experimental results are based on a multi-model dataset from 24 volunteers. Eventually, the lipreading accuracy of our framework was increased by 2.3% compared with existing systems, and our framework made progress in audio-visual fusion in a high noise environment compared with the system of audio recognition without visual.

Keywords: lipreading, audio-visual, Efficientnet, distillation

Procedia PDF Downloads 134

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 114

Authors: Madhavi

Abstract:

All linguistic units are context-dependent. They occur in particular settings, from which they derive much of their import, and are recognized by speakers as distinct entities only through a process of abstraction. Most of the words have several concepts associated with them and convey a number of meanings in different contexts in any language. For instance, there are different uses of the word good as an adjective from English. The adjective good expresses many senses like (1) ‘high quality of someone or something’ (2) ‘efficient’ (3) ‘virtuous’ (4) ‘reliable’ etc. These senses will be analyzed by using cognitive semantics framework. The context has the power to insulate one meaning from all the other meanings in communication. This paper will provide a cognitive semantic analysis. The basic tenet of cognitive semantics is the sense of a word is the way we conceptualize it. Our conceptualization is based on the physical experience we go through. Cognitive semantics tries to capture this conceptualization in terms of some categories like schema, frame, and domain. Cognitive semantics is a subfield of cognitive linguistics. Cognitive linguistics studies the language creation, learning, and usage by the reference to human cognition. The semantic structure is conceptual structure which is related to the concepts which are the elements of reason and constitute the meanings of words and linguistic expressions. Cognitive semantics studies how our mind works for the meaning of any word and how it perceives meaning from the environment through senses and works to map with the knowledge which already exists in our mind through experience. In the present paper, the senses are further classified into some categories.

Keywords: cognitive, contexts, semantics, senses

Procedia PDF Downloads 221

Authors: Paulo Fernando Silva Filho, Elcio Hideiti Shiguemori

Abstract:

The selection of specific landmarks for an Unmanned Aerial Vehicles’ Visual Navigation systems based on Automatic Landmark Recognition has significant influence on the precision of the system’s estimated position. At the same time, manual selection of the landmarks does not guarantee a high recognition rate, which would also result on a poor precision. This work aims to develop an automatic landmark selection that will take the image of the flight area and identify the best landmarks to be recognized by the Visual Navigation Landmark Recognition System. The criterion to select a landmark is based on features detected by ORB or AKAZE and edges information on each possible landmark. Results have shown that disposition of possible landmarks is quite different from the human perception.

Keywords: clustering, edges, feature points, landmark selection, X-means

Procedia PDF Downloads 282

Authors: Jayashree Aanand, Gajjam

Abstract:

The grammatical tradition in Sanskrit literature emphasizes the importance of the correct use of Sanskrit words or linguistic units (sādhu śabda) that brings the meritorious values, denying the attribution of the same religious merit to the incorrect use of Sanskrit words (asādhu śabda) or the vernacular or corrupt forms (apa-śabda or apabhraṁśa), even though they may help in communication. The current research, the culmination of the doctoral research on sentence definition, studies the difference among the comprehension of both correct and incorrect word forms in Sanskrit and Marathi languages in India. Based on the total of 19 experiments (both web-based and classroom-controlled) on approximately 900 Indian readers, it is found that while the incorrect forms in Sanskrit are comprehended with lesser accuracy than the correct word forms, no such difference can be seen for the Marathi language. It is interpreted that the incorrect word forms in the native language or in the language which is spoken daily (such as Marathi) will pose a lesser cognitive load as compared to the language that is not spoken on a daily basis but only used for reading (such as Sanskrit). The theoretical base for the research problem is as follows: among the three main schools of Language Science in ancient India, the Vaiyākaraṇas (Grammarians) hold that the corrupt word forms do have their own expressive power since they convey meaning, while as the Mimāṁsakas (the Exegesists) and the Naiyāyikas (the Logicians) believe that the corrupt forms can only convey the meaning indirectly, by recalling their association and similarity with the correct forms. The grammarians argue that the vernaculars that are born of the speaker’s inability to speak proper Sanskrit are regarded as degenerate versions or fallen forms of the ‘divine’ Sanskrit language and speakers who could not use proper Sanskrit or the standard language were considered as Śiṣṭa (‘elite’). The different ideas of different schools strictly adhere to their textual dispositions. For the last few years, sociolinguists have agreed that no variety of language is inherently better than any other; they are all the same as long as they serve the need of people that use them. Although the standard form of a language may offer the speakers some advantages, the non-standard variety is considered the most natural style of speaking. This is visible in the results. If the incorrect word forms incur the recall of the correct word forms in the reader as the theory suggests, it would have added one extra step in the process of sentential cognition leading to more cognitive load and less accuracy. This has not been the case for the Marathi language. Although speaking and listening to the vernaculars is the common practice and reading the vernacular is not, Marathi readers have readily and accurately comprehended the incorrect word forms in the sentences, as against the Sanskrit readers. The primary reason being Sanskrit is spoken and also read in the standard form only and the vernacular forms in Sanskrit are not found in the conversational data.

Keywords: experimental sociolinguistics, grammaticality and meaningfulness, Marathi, Sanskrit

Procedia PDF Downloads 127

Authors: Nawab Yousuf Ali, S. Golam, A. Ameer, Ashok Toru Roy

Abstract:

This paper develops new morphological rules suitable for Bangla repetition words to be incorporated into an inter lingua representation called Universal Networking Language (UNL). The proposed rules are to be used to combine verb roots and their inflexions to produce words which are then combined with other similar types of words to generate repetition words. This paper outlines the format of morphological rules for different types of repetition words that come from verb roots based on the framework of UNL provided by the UNL centre of the Universal Networking Digital Language (UNDL) foundation.

Keywords: Universal Networking Language (UNL), universal word (UW), head word (HW), Bangla-UNL Dictionary, morphological rule, enconverter (EnCo)

Procedia PDF Downloads 311

Authors: Alaaeldin Hamdy Ahmed Mohammed

Abstract:

Introduction: This study examines sports’ fans and non-interested public perception and recognition of the problems that have negative impacts upon the Egyptian sports, particularly football, through caricatures. Eight caricature paintings were designed to express eight problems affecting the Egyptian sports and its development. These paintings were distributed on two groups of the fans and the non-interested public. Methods: The study was limited to eight caricatures representing the eight issues which are: the impact of stopping the sports activity on athletes, the effect of clubs’ disagreement, fanaticism between the members of the ultras of different clubs, the negative impact of the mingling of politics into sports, the negative role of the clubs affects the professionalism of the promising players, the conflict between the national organization responsible for sports, the breaking in of the fans to the playgrounds, the impact of the lack of planning on the national team. The Results: The results showed that both sports fans and those who are not interested in sports recognized the problems that the caricatures refer to and criticizes exaggeration although the rate was higher for the fans. These caricatures contributed also in their recognition of the danger of the negative impact of these problems on the Egyptian sports, particularly football which is the most common at the Egyptian sports fans. Discussion: This finding echoes the conclusion that caricatures are distinctive in the adults’ facial stimuli that are either systematically exaggerated recognition of them.

Keywords: caricature, fans, football, sports

Procedia PDF Downloads 318

Authors: Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim

Abstract:

All currencies around the world look very different from each other. For instance, the size, color, and pattern of the paper are different. With the development of modern banking services, automatic methods for paper currency recognition become important in many applications like vending machines. One of the currency recognition architecture’s phases is Feature detection and description. There are many algorithms that are used for this phase, but they still have some disadvantages. This paper proposes a feature detection algorithm, which merges the advantages given in the current SIFT and SURF algorithms, which we call, Speeded up Robust Scale-Invariant Feature Transform (SR-SIFT) algorithm. Our proposed SR-SIFT algorithm overcomes the problems of both the SIFT and SURF algorithms. The proposed algorithm aims to speed up the SIFT feature detection algorithm and keep it robust. Simulation results demonstrate that the proposed SR-SIFT algorithm decreases the average response time, especially in small and minimum number of best key points, increases the distribution of the number of best key points on the surface of the currency. Furthermore, the proposed algorithm increases the accuracy of the true best point distribution inside the currency edge than the other two algorithms.

Keywords: currency recognition, feature detection and description, SIFT algorithm, SURF algorithm, speeded up and robust features

Procedia PDF Downloads 235

Authors: Saeedeh Barzegar Khalilsaraei, Manoocheher Kelarestaghi, Farshad Eshghi

Abstract:

The vehicle color, as a prominent and stable feature, helps to identify a vehicle more accurately. As a result, vehicle color recognition is of great importance in intelligent transportation systems. Unlike conventional methods which use only a single Convolutional Neural Network (CNN) for feature extraction or classification, in this paper, four CNNs, with different architectures well-performing in different classes, are trained to extract various features from the input image. To take advantage of the distinct capability of each network, the multiple outputs are combined using a stack generalization algorithm as an ensemble technique. As a result, the final model performs better than each CNN individually in vehicle color identification. The evaluation results in terms of overall average accuracy and accuracy variance show the proposed method’s outperformance compared to the state-of-the-art rivals.

Keywords: Vehicle Color Recognition, Ensemble Algorithm, Stack Generalization, Convolutional Neural Network

Procedia PDF Downloads 85

Authors: A. Degale Desta, Tamirat Kebamo

Abstract:

Background: Recent advances in computer vision and pattern recognition have significantly improved activity recognition through video analysis, particularly with the application of Deep Convolutional Neural Networks (CNNs). One-stage detectors now enable efficient video-based recognition by simultaneously predicting object categories and locations. Such advancements are highly relevant in educational settings where CCTV surveillance could automatically monitor academic activities, enhancing security and classroom management. However, current datasets and recognition systems lack the specific focus on campus environments necessary for practical application in these settings.Objective: This study aims to address this gap by developing a dataset and testing an automated activity recognition system specifically tailored for educational campuses. The EthioCAD dataset was created to capture various classroom activities and teacher-student interactions, facilitating reliable recognition of academic activities using deep learning models. Method: EthioCAD, a novel video-based dataset, was created with a design science research approach to encompass teacher-student interactions across three domains and 18 distinct classroom activities. Using the Roboflow AI framework, the data was processed, with 4.224 KB of frames and 33.485 MB of images managed for frame extraction, labeling, and organization. The Ultralytics YOLOv8 model was then implemented within Google Colab to evaluate the dataset’s effectiveness, achieving high mean Average Precision (mAP) scores. Results: The YOLOv8 model demonstrated robust activity recognition within campus-like settings, achieving an mAP50 of 90.2% and an mAP50-95 of 78.6%. These results highlight the potential of EthioCAD, combined with YOLOv8, to provide reliable detection and classification of classroom activities, supporting automated surveillance needs on educational campuses. Discussion: The high performance of YOLOv8 on the EthioCAD dataset suggests that automated activity recognition for surveillance is feasible within educational environments. This system addresses current limitations in campus-specific data and tools, offering a tailored solution for academic monitoring that could enhance the effectiveness of CCTV systems in these settings. Conclusion: The EthioCAD dataset, alongside the YOLOv8 model, provides a promising framework for automated campus activity recognition. This approach lays the groundwork for future advancements in CCTV-based educational surveillance systems, enabling more refined and reliable monitoring of classroom activities.

Keywords: deep CNN, EthioCAD, deep learning, YOLOv8, activity recognition

Procedia PDF Downloads 17

Authors: Lanchi Xie, Zhihui Li, Zhigang Li, Guiqiang Wang, Lei Xu, Yuwen Yan

Abstract:

Image-based facial features can be classified into category recognition features and individual recognition features. Current automated face recognition systems extract a specific feature vector of different dimensions from a facial image according to their pre-trained neural network. However, to improve the efficiency of parameter calculation, an algorithm generally reduces the image details by pooling. The operation will overlook the details concerned much by forensic experts. In our experiment, we adopted a variety of face recognition algorithms based on deep learning, compared a large number of naturally collected face images with the known data of the same person's frontal ID photos. Downscaling and manual handling were performed on the testing images. The results supported that the facial recognition algorithms based on deep learning detected structural and morphological information and rarely focused on specific markers such as stains and moles. Overall performance, distribution of genuine scores and impostor scores, and likelihood ratios were tested to evaluate the accuracy of biometric systems and forensic experts. Experiments showed that the biometric systems were skilled in distinguishing category features, and forensic experts were better at discovering the individual features of human faces. In the proposed approach, a fusion was performed at the score level. At the specified false accept rate, the framework achieved a lower false reject rate. This paper contributes to improving the interpretability of the objective method of facial comparison and provides a novel method for human-machine collaboration in this field.

Keywords: likelihood ratio, automated facial recognition, facial comparison, biometrics

Procedia PDF Downloads 130

Authors: Jun Gil Ahn, Jong Kang Park, Jong Tae Kim

Abstract:

In this paper, we analyze major components of activity recognition (AR) in wearable device with 9-axis sensors and sensor fusion filters. 9-axis sensors commonly include 3-axis accelerometer, 3-axis gyroscope and 3-axis magnetometer. We chose sensor fusion filters as Kalman filter and Direction Cosine Matrix (DCM) filter. We also construct sensor fusion data from each activity sensor data and perform classification by accuracy of AR using Naïve Bayes and SVM. According to the classification results, we observed that the DCM filter and the specific combination of the sensing axes are more effective for AR in wearable devices while classifying walking, running, ascending and descending.

Keywords: accelerometer, activity recognition, directiona cosine matrix filter, gyroscope, Kalman filter, magnetometer

Procedia PDF Downloads 333

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 275

Authors: Carlos Vera, Tetyana Baydyk, Ernst Kussul, Graciela Velasco, Miguel Aparicio

Abstract:

This article describes the Random Subspace Neural Classifier (RSC) for the recognition of meteors in the night sky. We used images of meteors entering the atmosphere at night between 8:00 p.m.-5: 00 a.m. The objective of this project is to classify meteor and star images (with stars as the image background). The monitoring of the sky and the classification of meteors are made for future applications by scientists. The image database was collected from different websites. We worked with RGB-type images with dimensions of 220x220 pixels stored in the BitMap Protocol (BMP) format. Subsequent window scanning and processing were carried out for each image. The scan window where the characteristics were extracted had the size of 20x20 pixels with a scanning step size of 10 pixels. Brightness, contrast and contour orientation histograms were used as inputs for the RSC. The RSC worked with two classes and classified into: 1) with meteors and 2) without meteors. Different tests were carried out by varying the number of training cycles and the number of images for training and recognition. The percentage error for the neural classifier was calculated. The results show a good RSC classifier response with 89% correct recognition. The results of these experiments are presented and discussed.

Keywords: contour orientation histogram, meteors, night sky, RSC neural classifier, stars

Procedia PDF Downloads 140

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 31

Authors: Yuh-Jen Wu, Chun-Min Lin

Abstract:

Homophonic words are common in Mandarin Chinese which belongs to the tonal language family. Using homophonic cues to study foreign languages is one of the learning techniques of mnemonics that can aid the retention and retrieval of information in the human memory. When learning difficult foreign words, some learners transpose them with words in a language they are familiar with to build an association and strengthen working memory. These phonological clues are beneficial means for novice language learners. In the classroom, if mnemonic skills are used at the appropriate time in the instructional sequence, it may achieve their maximum effectiveness. For Chinese-speaking students, proper use of Chinese-English homophonic word pairs may help them learn difficult vocabulary. In this study, a database program is developed by employing Visual Basic. The database contains two corpora, one with Chinese lexical items and the other with English ones. The Chinese corpus contains 59,053 Chinese words that were collected by a web crawler. The pronunciations of this group of words are compared with words in an English corpus based on WordNet, a lexical database for the English language. Words in both databases with similar pronunciation chunks and batches are detected. A total of approximately 1,000 Chinese lexical items are located in the preliminary comparison. These homophonic word pairs can serve as a valuable tool to assist Chinese-speaking students in learning and memorizing new English vocabulary.

Keywords: Chinese, corpus, English, homophonic words, vocabulary

Procedia PDF Downloads 185

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we present the human action recognition method using the variational Bayesian HMM with the Dirichlet process mixture (DPM) of the Gaussian-Wishart emission model (GWEM). First, we define the Bayesian HMM based on the Dirichlet process, which allows an infinite number of Gaussian-Wishart components to support continuous emission observations. Second, we have considered an efficient variational Bayesian inference method that can be applied to drive the posterior distribution of hidden variables and model parameters for the proposed model based on training data. And then we have derived the predictive distribution that may be used to classify new action. Third, the paper proposes a process of extracting appropriate spatial-temporal feature vectors that can be used to recognize a wide range of human behaviors from input video image. Finally, we have conducted experiments that can evaluate the performance of the proposed method. The experimental results show that the method presented is more efficient with human action recognition than existing methods.

Keywords: human action recognition, Bayesian HMM, Dirichlet process mixture model, Gaussian-Wishart emission model, Variational Bayesian inference, prior distribution and approximate posterior distribution, KTH dataset

Procedia PDF Downloads 355

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 341

Authors: M. C. Padma, R. J. Prathibha

Abstract:

Parts of speech tagging is the process of assigning appropriate parts of speech tags to the words in a given text. The critical or crucial information needed for tagging a word come from its internal structure rather from its neighboring words. The internal structure of a word comprises of its morphological features and grammatical information. This paper presents a morpheme based parts of speech tagger for Kannada language. This proposed work uses hierarchical tag set for assigning tags. The system is tested on some Kannada words taken from EMILLE corpus. Experimental result shows that the performance of the proposed system is above 90%.

Keywords: hierarchical tag set, morphological analyzer, natural language processing, paradigms, parts of speech

Procedia PDF Downloads 296

Authors: Hamza Iftikhar

Abstract:

The research study focuses on the transgender community's gender recognition challenges. It is one of the issues for the transgender community, interacting directly with the difficulties of gender identity and the lives of these people who are facing gender disapproval from society. This study investigates the major flaws of the transgender act. The study's goal is to look into the strange implications of self-perceived identity as a policy tool for transgender recognition. This policy tool jeopardises the rights of Pakistan's indigenous gender-variant people as well as the country's legal and social framework. Qualitative research using semi structured interviews will be carried out. This study proposes developing a scheme for mainstreaming gender-variant people on the basis of the Pakistani Constitution, Supreme Court guidelines, and internationally recognised principles of law. This would necessitate a thorough review of current law using a new approach and reference point.

Keywords: transgender act, self perceived identity, gender variant, policy tool

Procedia PDF Downloads 117

Authors: Elena E. Lyakso, Olga V. Frolova, Yuri N. Matveev, Aleksey S. Grigorev, Alexander S. Nikolaev, Viktor A. Gorodnyi

Abstract:

The study of the children’s emotional sphere depending on age and psychoneurological state is of great importance for the design of educational programs for children and their social adaptation. Atypical development may be accompanied by violations or specificities of the emotional sphere. To study characteristics of the emotional state reflection in the voice and speech features of children, the perceptual study with the participation of adults and the automatic recognition of speech were conducted. Speech of children with typical development (TD), with Down syndrome (DS), and with autism spectrum disorders (ASD) aged 6-12 years was recorded. To obtain emotional speech in children, model situations were created, including a dialogue between the child and the experimenter containing questions that can cause various emotional states in the child and playing with a standard set of toys. The questions and toys were selected, taking into account the child’s age, developmental characteristics, and speech skills. For the perceptual experiment by adults, test sequences containing speech material of 30 children: TD, DS, and ASD were created. The listeners were 100 adults (age 19.3 ± 2.3 years). The listeners were tasked with determining the children’s emotional state as “comfort – neutral – discomfort” while listening to the test material. Spectrographic analysis of speech signals was conducted. For automatic recognition of the emotional state, 6594 speech files containing speech material of children were prepared. Automatic recognition of three states, “comfort – neutral – discomfort,” was performed using automatically extracted from the set of acoustic features - the Geneva Minimalistic Acoustic Parameter Set (GeMAPS) and the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS). The results showed that the emotional state is worse determined by the speech of TD children (comfort – 58% of correct answers, discomfort – 56%). Listeners better recognized discomfort in children with ASD and DS (78% of answers) than comfort (70% and 67%, respectively, for children with DS and ASD). The neutral state is better recognized by the speech of children with ASD (67%) than by the speech of children with DS (52%) and TD children (54%). According to the automatic recognition data using the acoustic feature set GeMAPSv01b, the accuracy of automatic recognition of emotional states for children with ASD is 0.687; children with DS – 0.725; TD children – 0.641. When using the acoustic feature set eGeMAPSv01b, the accuracy of automatic recognition of emotional states for children with ASD is 0.671; children with DS – 0.717; TD children – 0.631. The use of different models showed similar results, with better recognition of emotional states by the speech of children with DS than by the speech of children with ASD. The state of comfort is automatically determined better by the speech of TD children (precision – 0.546) and children with ASD (0.523), discomfort – children with DS (0.504). The data on the specificities of recognition by adults of the children’s emotional state by their speech may be used in recruitment for working with children with atypical development. Automatic recognition data can be used to create alternative communication systems and automatic human-computer interfaces for social-emotional learning. Acknowledgment: This work was financially supported by the Russian Science Foundation (project 18-18-00063).

Keywords: autism spectrum disorders, automatic recognition of speech, child’s emotional speech, Down syndrome, perceptual experiment

Procedia PDF Downloads 190

Authors: Anna Jagielska

Abstract:

Five years ago, the word ‘gender’ was discussed in Poland exclusively in academic contexts. One year later, it was chosen as the word of the year and omnipresent in the Polish media. The rapid career of this word is due to the involvement of the Polish church hierarchy who strategically brought this term into relation with abortion, pornography and paedophilia. ‘Gender’ is more than a political slogan. It is a symbol of social anxiety and moral panic in Poland which need to be historically considered. The aim of this paper is to present selected rhetorical strategies used by the Polish Catholic clergy who strive to have an impact on the current gender discourse in Poland. In particular, the gender debate, culminated in the pastoral letter of the Bishops' Conference of Poland, will be discussed. The church’s protest against the Council of Europe’s Convention on Preventing and Combating Violence against Women and Domestic Violence will be analyzed and the recent heated debates in Poland on contraception, abortion, in vitro fertilization, and sex education will be mentioned. To provide explanations on the specificity of Polish gender debates the role of the Catholic Church in the fall of communism in Poland as well as the charismatisation of Polish society by Pope John Paul II will be explained. The social constructions of communism and feminism which are manifested in both written and symbolic contracts on gender equality between the Church and the State will be demonstrated. At the end of the paper, theories about the changing role of religion in society will be applied.

Keywords: gender, Poland, religion, catholicism, feminism

Procedia PDF Downloads 292

Authors: K. Veluraja

Abstract:

Glycan of glycolipids and glycoproteins is playing a significant role in living systems particularly in molecular recognition processes. Molecular recognition processes are attributed to their occurrence on the surface of the cell, sequential arrangement and type of sugar molecules present in the oligosaccharide structure and glyosidic linkage diversity (glycoinformatics) and conformational diversity (glycoconformatics). Molecular Dynamics Simulation study is a theoretical-cum-computational tool successfully utilized to establish glycoconformatics of glycan. The study on various oligosaccharides of glycan clearly indicates that oligosaccharides do exist in multiple conformational states and these conformational states arise due to the flexibility associated with a glycosidic torsional angle (φ,ψ) . As an example: a single disaccharide structure NeuNacα(2-3) Gal exists in three different conformational states due to the differences in the preferential value of glycosidic torsional angles (φ,ψ). Hence establishing three dimensional structural and conformational models for glycan (cartesian coordinates of every individual atoms of an oligosaccharide structure in a preferred conformation) is quite crucial to understand various molecular recognition processes such as glycan-toxin interaction and glycan-virus interaction. The gycoconformatics models obtained for various glycan through Molecular Dynamics Simulation stored in our 3DSDSCAR (3DSDSCAR.ORG) a public domain database and its utility value in understanding the molecular recognition processes and in drug design venture will be discussed.

Keywords: glycan, glycoconformatics, molecular dynamics simulation, oligosaccharide

Procedia PDF Downloads 138

Authors: Panagiotis Pentaris

Abstract:

The issue of social and legal recognition of LGBTQ families is of high importance when exploring the possibility of a family. Of equal importance is the fact that both society and the individual contribute to the overall recognition of LGBTQ families. This paper is a conceptual discussion, by methodology, of both sides; it uses a method of constructive analysis to expound on this issue. This method’s aim is to broaden conceptual theory, and introduce a new relationship between concepts that were previously not associated by evidence. This exploration has found that LGBTQ realities from an international perspective may differ and both legal and social rights are critical toward self-consciousness and the formation of a family. This paper asserts that internalised and historic oppression of LGBTQ individuals, places them, not always and not in all places, in a disadvantageous position as far as engaging with the potential of forming a family goes. The paper concludes that lack of social recognition and internalised oppression are key barriers regarding LGBTQ families.

Keywords: family, gay, self-worth, LGBTQ, social rights

Procedia PDF Downloads 125

Authors: Somar Boubou, Tatsuo Narikiyo, Michihiro Kawanishi

Abstract:

In this work, we address the problem of 3D object recognition with depth sensors such as Kinect or Structure sensor. Compared with traditional approaches based on local descriptors, which depends on local information around the object key points, we propose a global features based descriptor. Proposed descriptor, which we name as Differential Histogram of Normal Vectors (DHONV), is designed particularly to capture the surface geometric characteristics of the 3D objects represented by depth images. We describe the 3D surface of an object in each frame using a 2D spatial histogram capturing the normalized distribution of differential angles of the surface normal vectors. The object recognition experiments on the benchmark RGB-D object dataset and a self-collected dataset show that our proposed descriptor outperforms two others descriptors based on spin-images and histogram of normal vectors with linear-SVM classifier.

Keywords: vision in control, robotics, histogram, differential histogram of normal vectors

Procedia PDF Downloads 280

Authors: Bubai Maji, Monorama Swain

Abstract:

Speech is considered an essential and most natural medium for the interaction between machines and humans. However, extracting effective features for speech emotion recognition (SER) is remains challenging. The present studies show that the temporal information captured but high-level temporal-feature learning is yet to be investigated. In this paper, we present an efficient novel method using the Self-attention (SA) mechanism in a combination of Convolutional Neural Network (CNN) and Bi-directional Gated Recurrent Unit (Bi-GRU) network to learn high-level temporal-feature. In order to further enhance the representation of the high-level temporal-feature, we integrate a Bi-GRU output with learnable weights features by SA, and improve the performance. We evaluate our proposed method on our created SITB-OSED and IEMOCAP databases. We report that the experimental results of our proposed method achieve state-of-the-art performance on both databases.

Keywords: Bi-GRU, 1D-CNNs, self-attention, speech emotion recognition

Procedia PDF Downloads 114

Authors: Reem Alsager, James Milton

Abstract:

Coxhead’s (2000) Academic Word List (AWL) believed to be essential for students pursuing higher education and helps differentiate English for Academic Purposes (EAP) from General English as a course of study, and it is thought to be important for comprehending English academic texts. It has been described that AWL is an infrequent, discrete set of vocabulary items unreachable from general language. On the other hand, it has been known for a period of time that general vocabulary knowledge is a good predictor of academic achievement. This study, however, is an attempt to measure and compare the contribution of academic knowledge and general vocabulary knowledge to learners’ GPA and examine what knowledge is a better predictor of academic achievement and investigate whether AWL as a specialised list of infrequent words relates to the frequency effect. The participants were comprised of 44 international postgraduate students in Swansea University, all from the School of Management, following the taught MSc (Master of Science). The study employed the Academic Vocabulary Size Test (AVST) and the XK_Lex vocabulary size test. The findings indicate that AWL is a list based on word frequency rather than a discrete and unique word list and that the AWL performs the same function as general vocabulary, with tests of each found to measure largely the same quality of knowledge. The findings also suggest that the contribution that AWL knowledge provides for academic success is not sufficient and that general vocabulary knowledge is better in predicting academic achievement. Furthermore, the contribution that academic knowledge added above the contribution of general vocabulary knowledge when combined is really small and noteworthy. This study’s results are in line with the argument and suggest that it is the development of general vocabulary size is an essential quality for academic success and acquiring the words of the AWL will form part of this process. The AWL by itself does not provide sufficient coverage, and is probably not specialised enough, for knowledge of this list to influence this general process. It can be concluded that AWL as an academic word list epitomizes only a fraction of words that are actually needed for academic success in English and that knowledge of academic vocabulary combined with general vocabulary knowledge above the most frequent 3000 words is what matters most to ultimate academic success.

Keywords: academic achievement, academic vocabulary, general vocabulary, vocabulary size

Procedia PDF Downloads 220