Facial Expression Recognition for Learning Status Analysis

A hybrid model comprised of Gaussian Mixtures Models (GMMs) and Hidden Markov Models (HMMs) is used to model generic sounds with large intra class perceptual variations. Each class has variable number of mixture components in the GMM. The number of mixture components is derived using the Minimum Description Length (MDL) criterion. The overall performance of the hybrid model was compared against models based on HMMs and GMMs with a fixed number of mixture components across all classes. We show that a hybrid model outperforms both class-based GMMs, HMMs, and GMMs based on fixed number of components. Further, our experiments revealed that the contribution of transitions between states in HMMs has no significant effect on the overall classification performance of generic sounds when large intra class perceptual variations are present among sounds in the training and test datasets. Sounds that show multi-event structure with events that tend to be similar (repetitive) indicated improved performance when modeled with HMMs that can be attributed to HMM’s state transition property. Conversely, GMMs indicate better performance when the sound samples show subtle or no repetitive behavior. These results were validated using the MuscleFish sound database.

Feature mapping technique is widely used to eliminate the mismatch between the training and test conditions of speech recognition. In the feature mapping, a target (mismatched) feature vector sequence is mapped closer to the corresponding reference (matched) feature vector stream. The training of the mapping system is usually carried out based on a set of stereo data which consists of simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to blind parameter estimation which does not require the reference feature vectors. The proposed approach is motivated by the hidden Markov model (HMM)-based speech synthesis algorithm.

Students' course completion rate in distance education is getting attention of the researchers throughout the globe. Many factors responsible for high non completion rate of students in distance education are job responsibilities, domestic pressure and complexity of course content. Some researchers reported psychological reasons for dropout like, feeling of inadequacy, distress (Rickinson and Rutherford, 1996); lack of confidence (Cullen, 1994) examination anxiety (Fan and Chan, 1997). In literature lack of motivation is considered as the major responsible factor for this problem as students generally feel lonely due to lack of communication & competition in distance education. In this article effectiveness of ARCS Model of Motivational Design to overcome the motivational problem of distance learning students is discussed. The study indicate that the systems which are developed on the basis of ARCS Model raise the attention of the students during instruction, develop a relevance to the students' requirements, create a positive expectation for success and help having a satisfaction by reinforcing success.

In this dissertation, a novel approach of integrating template matching with statistical modeling is proposed to improve continuous speech recognition. Hidden Markov Modeling (HMMs) has been the dominant approach in statistical speech recognition since it provides a principled way of jointly modeling speech spectral variations and time dynamics. However, HMMs have the shortcoming of assuming the observations being independent within each state, which makes it ineffective in modeling the details of speech temporal evolutions that are important for characterizing nonstationary speech sounds. Template-based methods make comparisons between a test pattern and the templates derived from training data, and therefore they are able to capture speech dynamics and time correlation of speech frames better than HMM based methods. However, template matching requires large memory space and computational time since feature vectors of training data need to be stored in computer memory for access at the recognition stage, which is difficult in large vocabulary continuous speech recognition (LVCSR). Our proposed approach takes advantages of both statistical modeling and template matching, which overcomes the weakness of conventional template-based method and is feasible for LVCSR. We use multiple Gaussian Mixture Model (GMM) indices to represent each frame of speech templates, and define the template unit to be context-dependent phone segments (triphone context). We also use phonetic decision trees borrowed from those commonly used in HMMs to tie triphone templates and predict triphones unseen in training data. Two local distances, log likelihood ratio (LLR) and Kullback-Leibler (KL) divergence, are proposed for dynamic time warping (DTW) based template matching. In order to reduce computational complexity and storage space, we propose methods of minimum distance template selection (MDTS) and maximum log-likelihood template selection (MLTS), and investigate a template compression method on top of template selection to further improve recognition performance. The template based methods were used to rescore lattices generated by baseline HMMs on the tasks of TIMIT continuous phone recognition and teleheath LVCSR and experimental results demonstrated that the proposed approach of integrating template matching with statistical modeling significantly improved recognition performances over the HMM baselines. The template selection methods also provided significant recognition accuracy improvements over the HMM baseline while largely reducing the computation and storage complexities. When all templates or MDTS were used, using the LLR local distance obtained better recognition performance than the KL divergence local distance. For MLTS and template compression, KL divergence local distance provided better performance than the LLR local distance, and the template compression method made further improvements over KL based MLTS. Since the templates were constructed based on the GMM indices extracted from HMM baselines, we also validated the effectiveness of the proposed template methods based on enhanced HMM baselines. Experimental results showed that LLR based all template method was able to consistently improve TIMIT phone recognition accuracies based on four enhanced HMM baselines. Prosodic features such as duration, energy, and pitch can reflect longer span information of speech than conventional single frame vectors but they have commonly been ignored by HMMs. Template based methods provide possibilities to conveniently integrate prosodic features into speech recognition, which has not been well studied in the past. In this dissertation, we investigate combining template based methods with the speech prosodic features of duration, energy and pitch to further improve speech recognition accuracy. The scores of prosodic information were computed by a GMM based method and a non-parametric method, and the prosodic scores were combined with the acoustic scores in triphone template matching. Experimental results obtained on the telehealth task showed that prosodic information had positive effects on vowel sound recognition.

As distance education grows increasingly popular, higher educational institutions are finding it more challenging to retain this population than face-to-face students. Academic coaching has emerged as a possible technique for improving retention among distance education students. In this study, the researcher conducted an interpretive phenomenological analysis (IPA) through three semi-structured interviews with four undergraduate distance education students. The purpose of the study was to explore how undergraduate, distance education students experienced academic coaching provided by a private coaching company and how they perceived it to influence their retention. Ultimately, each interviewee felt that their academic coach contributed to their ability to be retained, which led the researcher to conclude that academic coaching can be an effective and powerful retention tool for distance education students.

Speech communication is fast gaining market penetration as a preferable input for human computer interface (HCI) and is finding its way into the commercial applications from the academic research setup. For public applications, acceptance is determined not only by the accuracy and reliability but the ease of usage and habituation. In this work, we show that accuracy of a system can be enhanced using Speaker Adaption Technique (SAT). Kaldi speech recognition toolkit was used to evaluate the performance of our Hindi speech model. Acoustic feature were extracted using MFCC and PLP from 1000 phonetically balanced Hindi sentence from AMUAV corpus. Acoustic model was trained using Hidden Markov Model and Gaussian Mixture Models (HMM-GMM) and decoding was performed using Weight Finite State Transducers (WFSTs). Maximum improvement of 6.93% in word error rate is obtained for speaker adaptive training when used along with Linear Discriminant Analysis-Maximum Likelihood Linear Transform model over monophone model.

We present a Histogram of Oriented Gradient (HoG) based two-directional Dynamic Time Warping (DTW) matching method for handwritten word spotting. Firstly, we extract HoG descriptors from each cell in the normalized images. Then we connect the HoG descriptors in the same column and get a sequence of feature vectors. We do the same operation for the HoG descriptors in the same row. We then apply the two-directional DTW method to calculate the distance between the feature vectors sequences extracted from the query word and the candidate one. The experimental results show that the two-directional DTW is more robust to word deformation than the traditional DTW. And the local features such as HoG, LBP and SIFT combined with the two-directional DTW method outperform the method using the local feature descriptors directly. The HoG based two-directional DTW get the highest mean average precision on both the George Washington dataset and the CASIA-HWDB 2.1 dataset.

Signature, a form of handwritten depiction, has been and is still widely used as a proof of the writer's identity/intent in human society. Online signatures represents the dynamic process of handwriting as a sequence of feature vectors along time. Dynamic time warping (DTW) has been popularly adopted to compare sequence data. A basic problem in using DTW for signature verification is how to estimate the difference between the feature vectors. Most previous researches made use of Euclidean distance (ED) for this problem. However, ED treats each feature equally and cannot take account of the correlations between features. To overcome this problem, this paper proposed Mahalanobis distance (MD) for signature verification. One key question is how to estimate covariance matrix in MD calculation. We formulate this problem in a learning framework and introduce two criterion for estimating the matrix. The first criteria aims at minimizing the signature difference for the same writer, while the second criteria try to maximize the signature difference between different writers while minimize the within-writer signature difference. We carried out experiments on the MCYT biometric database. The experimental results exhibit that the proposed MD based method achieved better results than ED based method.

International students are a group of rising prominence in open, distance, and digital higher education, although there is, at present, limited systematic data about their numbers worldwide. International students in open, distance, and digital education occupy an interesting “third space,” whereby they commonly remain within their home environment and surroundings while simultaneously studying from an institution-based abroad. This means that many of the lenses used to frame and categorize international students in face-to-face settings – mobility, visas, and citizenship – are found problematic in online distance settings. This chapter reflects on these issues to outline complexities in categorizing international students in open, distance, and digital higher education and the ways that their experiences may be distinct from international students who are geographically mobile. The chapter ends with a reflection on gaps in current research and suggestions for researchers who include international students in their work.

Following recent advancements in deep learning and artificial intelligence, spoken language identification applications are playing an increasingly significant role in our day-to-day lives, especially in the domain of multi-lingual speech recognition. In this article, we propose a spoken language identification system that depends on the sequence of feature vectors. The proposed system uses a hybrid Convolutional Recurrent Neural Network (CRNN), which combines a Convolutional Neural Network (CNN) with a Recurrent Neural Network (RNN) network, for spoken language identification on seven languages, including Arabic, chosen from subsets of the Mozilla Common Voice (MCV) corpus. The proposed system exploits the advantages of both CNN and RNN architectures to construct the CRNN architecture. At the feature extraction stage, it compares the Gammatone Cepstral Coefficient (GTCC) feature and Mel Frequency Cepstral Coefficient (MFCC) feature, as well as a combination of both. Finally, the speech signals were represented as frames and used as the input for the CRNN architecture. After conducting experiments, the results of the proposed system indicate higher performance with combined GTCC and MFCC features compared to GTCC or MFCC features used individually. The average accuracy of the proposed system was 92.81% in the best experiment for spoken language identification. Furthermore, the system can learn language-specific patterns in various filter size representations of speech files.

The main purpose of this study was to identify the challenges distance education students experience during their education degree studies. The specific objectives studied included the following: to investigate the technical and technology limitations, limited interactivity between lecturers and students and among distance education students, and lack of support from administrative staff. The research design employed in this study was the survey research design. The distance education students were asked to complete an online survey to determine their experiences doing their studies on a distance mode. The target population for this study included all distance education students (1675) who are enrolled at the Centre for Open, Distance and eLearning (CODEL) at the University of Namibia in 2020. The questionnaire instrument was administered via google form, 354 responses were received in spreadsheet formats, and chats generated from the responses, the Statistical Package of the Social Sciences (SPSS) file, the descriptive and reliability statistics for all the variables. Based on the findings of this study, this study concludes that the University of Namibia needs to improve slow internet speeds, limited internet access, lecturer student interaction, collaboration between distance education students, lack of computers, among others. Some of the recommendations made by this study include: increased funding in ICT infrastructure for distance education students, better training for lecturers on how to deliver pedagogy and the CODeL administrative staff to better support distance education students.

This paper argues that, apart from interactive activities, the perceptions of psychological presence that distance education students hold of their teachers, peer students, and the institution can be significant predictors of their learning. The "perception of presence" in this paper is defined as the degree to which a distance education student senses the availability of, and connectedness with, each party. This form of presence is designated here as "Transactional Presence" (TP). In this study, distance education student learning was assessed in the light of students' perceived learning achievement, satisfaction, and intent-to-persist. An analysis of student survey data indicates that a distance student's sense of institutional TP predicts all the selected measures to do with success in distance learning. While a sense of peer student TP is significantly related to satisfaction and intent-to-persist, the effect of teacher TP is found to relate only to student-perceived learning achievement. Implications of the TP construct are discussed with respect to the theory, research, and practice of distance education, along with recommendations for future research.

This study was designed to identify the causes of stress and coping strategies adopted among distance education students at the College of Distance Education in the University of Cape Coast. A total of 332 diploma and post-diploma final year students in 2014/2015 academic year were selected from two study centers using random sampling procedure to respond to self-administered questionnaire. The questionnaire which was adapted to suit the study context was pre-tested to ensure that it elicited valid response. The results of the study showed that ‘academic workload’, ‘high frequency of examinations’, ‘financial problems’, family/marriage problems’ were the major causes of stress among the students. The study also found some statistical significant differences between married and unmarried students with married students feeling more stressed with ‘financial problems’ and ‘family/marriage problems’ than unmarried students. Students used multiple strategies, mainly praying/meditating, self-distracting activities such as watching TV and listening to music to cope with stress. Other important stress coping strategies were emotional and instrumental support from family, friends and lecturers. The study recommended among others that the need for the counseling unit at College of Distance Education of UCC to organize frequent stress management programs for students and assign academic counselors to students.

The rapid development of technology from day to day has manifested itself also in the field of education, and therefore it has become compulsory to include new regulations in education. In this fast-paced development, technology is coming into prominence both in distance education and traditional education. In this context, the technological organization established has an important role in the emergence of success perception. Since computer has begun to be used in the field of education, in addition to traditional education, the distance education has become in a more effective and productive education for foreign language learners. In this study, the distance learning, traditional education, teaching environments and perception of organizing as academic achievement are explained. The study has been carried out in a private university in the academic year of 2016-2017. The aim of this study is to evaluate the perception of success between distance education and traditional education in the foreign language education. This study examined the perceptions of administrators, lecturers and students towards the distance learning and traditional learning in order to evaluate the academic success of organizing in foreign language learning. The qualitative data analysis was used in this study. Administrators and students reported that they were prepared to facilitate individual study and improve their work skills with distance learning in the foreign language learning, but that the lecturers were not in the same position with the administrators and students in distance education.

Classification of multi-variate time series data of varying length finds applications in various domains of science and technology. There are two paradigms for modeling multi-variate varying length time series, namely, modeling the sequences of feature vectors and modeling the sets of feature vectors in the time series. In tasks such as text independent speaker recognition, audio clip classification and speech emotion recognition, modeling temporal dynamics is not critical and there may not be any underlying constraint in the time series. Gaussian mixture models (GMM) are commonly used for these tasks. In this paper, we propose a method based on descriptive statistical features for multi-variate varying length time series classification. The proposed method reduces the dimensionality of representation significantly and is less sensitive to missing samples. The proposed method is applied on speech emotion recognition and audio clip classification. The performance is compared with that of the GMMs based approaches that use maximum likelihood method and variational Bayes method for parameter estimation, and two approaches that combine GMMs and SVMs, namely, score vector based approach and segment modeling based approach. The proposed method is shown to give a better performance compared to all other methods.