Computer Assisted Language Learning System Research Articles

Effectiveness of Computer Application in Improving Reading Skills in Chinese Language and Towards Post-Attitudes as Home-based Learning

Background: As technology continues to advance, language acquisition methodologies have increasingly been integrated into computer-assisted language learning (CALL) systems. In the context of Chinese language acquisition, characters are structured in three phases: the overall character, its components, and its strokes. Proficiency in identifying and distinguishing individual characters hinges upon understanding their structural composition. Objective: This study aims to explore the impact of a computer application on Chinese language reading skills and students' perceptions regarding the utilization of computer applications for home-based learning. Method: A total of 60 students engaged in home-based learning using a designated computer application were involved in the study. Employing a quantitative approach with a quasi-experimental design, the study assessed the effects of the intervention. Results and Conclusion: Following one month of home-based learning through computer applications, participants exhibited higher gain scores in reading skill tests, albeit the differences were not statistically significant. Students expressed a preference for and perceived greater ease in acquiring reading skills through computer applications compared to traditional methods. Furthermore, the integration of computer applications in teaching and learning processes demonstrated the potential to enhance students' motivation, interest, and confidence in language acquisition, albeit without a notable impact on attention levels. The study underscores the pedagogical promise of Computer-Assisted Language Learning (CALL) and advocates for further research endeavors in this domain.

Experimental Study on the Acoustic Characteristics of “Similar” Vowels in Mandarin Learners

Abstract The rapid globalization of regions with different languages necessitates more advanced non-native tongue proficiency among individuals who need to communicate across language barriers. To deal with this demand, the research conducts a comparative analysis of the acoustic features of similar sounds between standard Mandarin (L2) and Mandarin spoken by Uyghurs (L1). Flege’s Speech Learning Model as well as Lado’s Contrastive Analysis Hypothesis serve as the foundation for this study. First, an acoustic analysis of Mandarin Chinese vowels produced via Uyghur and native Mandarin speakers is carried out. Ten Mandarin speakers and ten Uyghur Chinese speakers were compared with respect to word-level productions, and the 1st, 2nd formant frequencies (F1, F2) for Mandarin vowels were studied. The comparative acoustic analysis results show that the production of four ‘similar’ vowels by male and female Uyghur Chinese speakers differs significantly from native Mandarin speakers. Second, the following features are seen when native Mandarin speakers and Uyghur Chinese speakers compare their vowel spaces: Uyghur speakers’ vowels have a lower F1, which means that their overall vowel space distribution is surpassing that of Chinese speakers’. Thirdly, the Euclidean Distance analysis of monophthongs produced via Uyghur as well as Mandarin Chinese speakers reveals a gender-specific applicability of the Speech Learning Model. While the model successfully explains the production of Mandarin monophthongs by Uyghur female speakers, it falls short in accounting for the production patterns observed in Uyghur male speakers. The research findings of this thesis contribute a new direction to future developments in research aimed at improving speech recognition and Computer-Assisted Language Learning (CALL) systems.

An ensemble-based framework for mispronunciation detection of Arabic phonemes

An ensemble-based framework for mispronunciation detection of Arabic phonemes

Using Statistical Test Method to Establish a Decision Model of Performance Evaluation Matrix

Many studies have pointed out that the Performance Evaluation Matrix (PEM) is a convenient and useful tool for the evaluation, analysis, and improvement of service operating systems. All service items of the operating system can collect customer satisfaction and importance through questionnaires and then convert them into satisfaction indices and importance indices to establish PEM and its evaluation rules. Since the indices have unknown parameters, if the evaluation is performed directly by the point estimates of the indices, there will be a risk of misjudgment due to sampling error. In addition, most of the studies only determine the critical-to-quality (CTQ) that needs to be improved, and do not discuss the treatment rules in the case of limited resources nor perform the confirmation after improvement. Therefore, to address similar research gaps, this paper proposed the unbiased estimators of these two indices and determined the critical-to-quality (CTQ) service items which need to be improved through the one-tailed statistical hypothesis test by building a PEM method of the satisfaction index. In addition, through the one-tailed statistical hypothesis test method of the importance index, the improvement priority of service items was determined under the condition of limited resources. Confirmation of the effect on improvement is an important step in management. Thus, this paper adopted a statistical two-tailed hypothesis test to verify whether the satisfaction of all the CTQ service items that need to be improved was enhanced. Since the method proposed in this paper was established through statistical hypothesis tests, the risk of misjudgment due to sampling error could be reduced. Obviously, reducing the misjudgment risk is the advantage of the method in this paper. Based on the precondition, utilizing the model in this study may assist the industries to determine CTQ rapidly, implement the most efficient improvement under the condition of limited resources and also confirm the improvement effect at the same time. Finally, a case study of computer-assisted language learning system (CALL System) was used to illustrate a way to apply the model proposed in this paper.

Utilizing Artificial Intelligence Technologies in Saudi EFL Tertiary Level Classrooms

This study focuses on the employment of AI technology in regular, day-to-day activities, such as when Google Translate or Bing Translator are encouraged alongside various programs and applications. It also evaluates and empirically demonstrates the subjects of writing with AI technologies, computer-assisted language learning (CALL), machine translation (MT), and automatic evaluation systems (AESs) in order to offer solutions for enhanced communication training in Saudi Arabia's EFL system. Word tune is an artificial intelligence (AI)-driven writing assistant that can understand the writer's ideas and suggest alternative rewrites (e.g., shorten, expand). This program assists writers of English as a foreign language to maintain a steady flow and acquire useful English expressions. This research made use of questionnaires as a method for collecting data and then ran those responses through SPSS for analysis. The use of artificial intelligence (AI) technology in English as a foreign language (EFL) settings has been shown to facilitate the English language learning (ELT) process and to keep both teachers and students up to date on recent technological developments. This exploratory investigation demonstrated that all digital and AI-powered devices have the potential to assist in teaching and learning. Consequently, the pedagogical component of future education can be developed using an AI framework.

Evaluation of a Computer-Assisted Language Learning System Based on Adaptive Learning Designed for Self-training in Scientific French Language

This article presents the development and evaluation of a computer-assisted language learning system designed for self-training in scientific French language. The main problem addressed by this research is the linguistic obstacles faced by students during their academic years, which inspired the implementation of an adaptive learning system personalized to their needs. The methodology applied involved a need analysis approach to better adapt the French language learning offer to students’ demand, followed by the development of an adaptive learning model based on Item Response Theory (IRT). The system was evaluated by the System Usability Scale (SUS) model which shows high usability and user satisfaction and engagement. The findings were very encouraging, demonstrating that the presented adaptive learning model improves the adaptability of students’ needs and preferences. Overall, the aim of this research is to prove that the proposed learning system will improve the learners’ performance and understanding of scientific French language.

Construction and Optimization of Artificial Intelligence-Assisted Interactive College Music Performance Teaching System

This research focuses on the relationship between artificial intelligence technology and music performance in colleges and universities and explores the application of artificial intelligence technology in music teaching. At the same time, it explores the deficiencies of existing computer-assisted language learning software and systems through questionnaires and interviews and also proposes solutions, such as further understanding of theories, enhancing learners’ confidence, and stimulating their interest in learning. The results of this research will help to improve the application of online intelligent human-computer systems in music teaching and provide dynamic support for improving the quality of music teaching and talent training in colleges and universities.

Application of Ontology Matching Algorithm Based on Linguistic Features in English Pronunciation Quality Evaluation.

Traditional English classroom teaching is difficult to meet the oral learning needs of most learners. Thanks to the continuous advancement of speech processing technology, computer-assisted language learning systems are becoming more intelligent, not only pointing out learners' pronunciation errors but also assessing their overall pronunciation level. Method. This paper uses the method of tree kernel function to measure the similarity of two ontology trees. According to the features of nodes in ontology tree, methods to calculate the external features and internal features of nodes are proposed, respectively. External features are mainly obtained by calculating the hierarchical centrality, node density, and node coverage of nodes in the ontology tree; internal features are mainly obtained by measuring the richness of internal information. According to the similarity of ontology tree and the external features and internal features of nodes, the calculation formula of structural comprehensive similarity is improved, and the features of ontology itself can be fully considered in the calculation. According to the difference of the structure, the weights of the corresponding features during the calculation are adjusted autonomously, so that the calculation results are closer to reality. In spectral image preprocessing, endpoint detection utilizes the harmonic characteristics presented by narrowband spectrograms with high frequency resolution and eliminates useless nonspeech segments by detecting the presence of voiced segments. When building the neural network model, four convolutional layers, two fully connected layers, and one softmax output layer were conceived, and dropout was used to randomly suspend the work of some neurons to avoid overfitting. Results/Discussion. Through the data analysis of mean and variance and verified by one-way analysis of variance, it proves that the sentiment evaluation method in this paper is effective. The traditional multiple linear regression method is not suitable for the corpus and application scenarios of this paper. This paper proposes a decision tree structure, which is similar to the overall scoring process of raters, and uses the Interactive Dicremiser version 3 (ID3) algorithm to build a comprehensive evaluation decision tree for pitch, rhythm, intonation, speech rate, and emotion indicators. It is proved by experiments that the accurate consistency rate of the human-machine evaluation in this paper is 93%, the adjacent consistency rate is 96%, and the Pearson correlation coefficient value of the human-machine evaluation results is 0.89. The data results prove that the evaluation method in this paper is credible.

Research on Network Oral English Teaching System Based on Machine Learning

With the development of computer science and technology and the advancement of language teaching and learning methods, computer-assisted language learning technology has made it possible to solve this problem. In the area of oral learning, some computer-assisted language learning systems at home and abroad mainly focus on the learning of words and grammar and only have one or two evaluation indicators as the basis of evaluation, which have certain functional defects and can only give an overall rating to learners’ pronunciation. To address these problems, this paper takes the English speech of Chinese college students as the research object and improves the traditional computerized English pronunciation quality evaluation method by considering multiplicative evaluation indexes, such as pitch, speed, rhythm, and intonation; i.e., pitch evaluation is based on frequency central feature parameters, speech speed evaluation based on speech duration, rhythm evaluation. The method of pitch, speed, rhythm, and intonation evaluation has been experimentally verified to be reliable. Furthermore, considering the weight of the above multiplicative evaluation indexes.

Language learning in an era of datafication and personalized learning

This perspective reviews the technical and educational accomplishments represented by Liu et al.’s (Educ Technol Res Dev 67: 1307–1331, 2019) computer-assisted language learning system. It then zooms out to view the system as an example of what the future of “shifting to digital” might look like. This is done by demonstrating how the authors’ system aligns with two emerging trends in education: datafication and personalized learning. The perspective concludes with constructive feedback and recommendations for future research.

Synthesizing a Japanese-language functional expression learning system with Chinese-speaking learners’ cultural interests and backgrounds

This piece is a short response to Liu, Shindo, and Matsumoto’s (2019) Development of a computer-assisted Japanese functional expression learning system for Chinese-speaking learners for the special issue: Shifting to Digital: Informing the rapid development, deployment, and future of teaching and learning. Key ideas, value, and future implications are culturally addressed in relation to a computer-assisted language learning system entitled Jastudy meant for Chinese learners of Japanese language.

Development and Application of a Performance Evaluation Matrix: A Case Study on Exploring the Items Considered Critical to Quality

Abstract A performance evaluation matrix is based on questionnaires collected from users or customers to pinpoint the performance of a system operation and furthermore to locate the items that need to be improved to upgrade the performance of system operations. To achieve this, this article proposes a discrimination index and applies statistics inference to deduce confidence intervals of the discrimination index. Meanwhile, we refer to Buckley’s fuzzy testing method to construct a fuzzy affiliation function and address a fuzzy evaluation criterion for exploring the items considered critical to quality to overcome the complicated problems of the questionnaires’ sampling error and interviewees’ fuzzy linguistics. The advantages of the method in this article are that it keeps the simple filling pattern of Likert’s scale and provides efficacy of data collection. Subsequently, we reduce the fuzzy linguistics and questionnaires’ sampling error by statistics inference and fuzzy hypothesis testing. Finally, we use a case study with the computer-assisted language learning system to demonstrate an application of the proposed method.

An Experiential Learning Approach to Learning Manual Communication Through a Virtual Reality Environment

There is a pressing need for effective pedagogical methods of manual languages, as evident in the decline of manual languages, such as New Zealand Sign Language (NZSL). Despite being recognized as one of New Zealand's official languages, recent censuses have shown that fluent NZSL signers have been steadily decreasing. There is a cultural responsibility to preserve such languages, yet the combination of barriers to acquisition and the limited availability of effective teaching methods are standing in the way. In light of this, this article proposes a computer-assisted sign language learning system that incorporates virtual reality and validation-based feedback as tools to implement the experiential learning model. An implementation in the form of virtual reality NZSL is presented, targeting the set of NZSL alphabet. Results show that a vision-based classification method, using the Leap Motion controller, is a scalable, accurate, and usable solution for feedback-assisted manual language learning. A formative usability evaluation of $n=10$ participants showed promising results for engagement, confidence, and memory retention. The results indicate that virtual reality technology is uniquely situated as an innovative medium for the self-directed acquisition of manual languages. It is hoped this article inspires technology researchers to pursue collaborations with the deaf/Deaf community to design and develop pedagogical technology solutions for manual communication.

Constructing Fuzzy Hypothesis Methods to Determine Critical-To-Quality Service Items

This paper constructs a performance evaluation matrix (PEM) with beta distribution. Beta is between zero and one, making it a suitable indicator to describe customer ratings of importance and satisfaction from 0% to 100%. According to the spirit of ceaseless improvement put forward by total quality management, the average ratings are set as the standard, and then the coordinates of each satisfaction and importance item is located in the performance areas. This makes it easy to identify critical-to-quality items that require improvement. However, the data collection method of questionnaires inevitably involves sampling error, and the opinions of customers are often ambiguous. To solve these problems, we constructed a fuzzy testing method based on confidence intervals. The use of confidence intervals decreases the chance of misjudgment caused by sampling errors, and more precisely gets closer to customers’ voices. This result is more reasonable than the traditional statistical testing principle. The proposed methods are applied to assessment of a computer-assisted language learning (CALL) system to display their competence.

Automatic assessment of English proficiency for Japanese learners without reference sentences based on deep neural network acoustic models

Abstract Speech-based computer-assisted language learning (CALL) systems should recognize the utterances of the learner with high accuracy and evaluate the language proficiency of the specific speaker with appropriate methods. In this paper, we discuss the automatic assessment of the second language (L2) for non-native speakers. There are many existing works on pronunciation evaluation by applying the goodness of pronunciation (GOP) method. This paper introduces an automatic proficiency evaluation system that combines various kinds of non-native acoustic models and native ones, such as Gaussian mixture model (GMM)-hidden Markov model (HMM) and deep neural network (DNN)-HMM. Most of existing works assume that we know the transcription of an utterance (the reference sentence) when evaluating the utterance, especially in reading and repeating tasks. To realize a reference-free proficiency evaluation, we propose a novel machine score named as the reference-free error rate (RER) to evaluate English proficiency. In our experiments, the DNN-based non-native acoustic models outperformed the traditional acoustic models on non-native speech recognition. Thus, we calculated the RER by regarding the recognition result from the DNN-based non-native acoustic model as “reference” and the result from the native acoustic model as “recognition result”. The proposed RER has high correlation with human proficiency scores, which indicates the effectiveness of RER for automatically estimating the proficiency. By combining the RER with other machine scores such as the log-likelihood scores, we obtained high correlation (reading aloud task: r = 0.826 , p 0.001 , N = 190 ; constrained interactive dialogue task: r = 0.803 , p 0.001 , N = 26 ; spontaneous English conversation task: r = 0.799 , p 0.001 , N = 28 ) to the human scores.

Fuzzy test model for performance evaluation matrix of service operating systems

Abstract The performance evaluation matrix is a useful and convenient tool for collecting user opinions and identifying service items that are in need of improvement in operating systems. It has been used in many studies looking for ways to increase the response willingness of customers and solve the problem of fuzziness in user opinions. Likert scales are simple and can increase the response willingness of customers and the efficiency of data collection. In contrast, fuzzy linguistic scales can more accurately capture the voice of the customer, but responding to them is a more complex matter and lowers the response willingness of customers. Confidence intervals can lower the risk of misjudgment caused by sampling errors in user opinion collection; the smaller the confidence intervals are, the lower the risk of misjudgment is. We therefore developed the Buckley fuzzy test methods that maintain the simplicity offered by Likert scales in collecting data. We used the indices confidence intervals derived from the data to construct fuzzy membership functions and develop our fuzzy test methods. Clearly, those approaches solve the problem of fuzziness in customer opinions without affecting the response willingness of customers. Those methods are grounded in confidence intervals, which reduce the risk of misjudgment caused by sampling errors. Furthermore, when confidence intervals are relatively wide due to cost and time considerations, the Buckley fuzzy test methods overcome this limitation by swiftly identifying service items that are in need of improvement in an operating system, as well as prioritizing service items using pair-wise comparisons of the influence indices of the service items. This enables the identification of the service items that should take priority when resources are limited. Finally, we used a case study involving a computer-assisted language learning system to demonstrate the applicability of the proposed approach.

A longitudinal observation of technology-mediated feedback for L2 learners of German

AbstractThis article provides a longitudinal study of L2 learners of German who used a computer-assisted language learning (CALL) system that formed part of their regular classroom instruction. The 42 learners were enrolled in four consecutive university language courses at a beginner and intermediate level. The study compares two different feedback types, metalinguistic feedback and repetition, which were provided for the same exercise type over the course of four semesters. The exercise type required learners to build sentences from a set of predefined, uninflected words. While the grammatical focus of the exercises changed over time, many of the same grammatical constructions were present in all four courses. The study discusses the changes in learner performance and error correction behavior as students became more proficient in their knowledge of the L2 grammar and were exposed to the technology-mediated feedback that remained consistent throughout system use over the four language courses.

Development of a computer-assisted Japanese functional expression learning system for Chinese-speaking learners

Because a large number of Chinese characters are commonly used in both Japanese and Chinese, Chinese-speaking learners of Japanese as a second language (JSL) find it more challenging to learn Japanese functional expressions than to learn other Japanese vocabulary. To address this challenge, we have developed Jastudy, a computer-assisted language learning (CALL) system designed specifically for Chinese-speaking learners studying Japanese functional expressions. Given a Japanese sentence as an input, the system automatically detects Japanese functional expressions using a character-based bidirectional long short-term memory with a conditional random field (BiLSTM-CRF) model. The sentence is then segmented and the parts of speech (POS) are tagged (word segmentation and POS tagging) by a Japanese morphological analyzer, MeCab ( http://taku910.github.io/mecab/ ), trained using a CRF model. In addition, the system provides JSL learners with appropriate example sentences that illustrate Japanese functional expressions. The system uses a ranking system, which gives easier sentences a higher rank, when selecting example sentences. A support vector machine for ranking (SVMRank) algorithm estimates the readability of example sentences, using Japanese-Chinese common words as an important feature. A k-means clustering algorithm is used to cluster example sentences that contain functional expressions with the same meanings, based on part-of-speech, conjugation form, and semantic attributes. Finally, to evaluate the usefulness of the system, we have conducted experiments and reported on a preliminary user study involving Chinese-speaking JSL learners.

Mispronunciation Detection Using Deep Convolutional Neural Network Features and Transfer Learning-Based Model for Arabic Phonemes

Computer-assisted language learning (CALL) systems provide an automated framework to identify mispronunciation and give useful feedback. Traditionally, handcrafted acoustic-phonetic features are used to detect mispronunciation. From this line of research, this paper investigates the use of the deep convolutional neural network for mispronunciation detection of Arabic phonemes. We propose two methods with different techniques, i.e., convolutional neural network features (CNN_Features)-based technique and a transfer learning-based technique to detect mispronunciation detection. In the first method, we use deep CNN features to detect mispronunciation. We also extract features from different layers of CNN (layer4 to layer7) to train k-nearest neighbor (KNN), support vector machine (SVM), and neural network (NN) classifiers. In the transfer learning-based method, we trained the CNN using transfer learning to detect mispronunciation. To evaluate the performance of the system, we compare the results of these methods with baseline handcrafted features-based method for 28 Arabic phonemes. In the baseline method, we use the same classifiers; KNN, SVM, and NN to detect mispronunciation. The experimental results show that handcrafted_features method, CNN_features, and transfer learning-based method achieve an accuracy of 82%, 91.7%, and 92.2%, respectively. The performance analysis shows that transfer learning-based method outperforms handcrafted_features and transfer CNN_features-based methods and achieve an accuracy of 92.2%. The proposed transfer learning-based method also outperforms the state-of-art techniques in term of accuracy.

Developing a Discriminant Index to Determine Critical Service Attributes of Continuous Performance Improvement

A performance evaluation matrix (PEM) presents the overall performance of an organization and provide reference for improvement strategies. PEMs are widely applied in the assessment of service performance in various organizations. Customer ratings of importance and satisfaction are used to calculate point estimates which are then plotted in PEMs. Their locations in the PEM show whether performance is good. Researchers have replaced these point estimates with the joint confidence interval of two indices to reduce the uncertainties caused by sampling errors and prevent misjudgment. However, this approach is quite complicated for practice application. For this reason, we defined a discriminant index based on PEM concepts. Our index uses the difference between the importance and satisfaction indices to solve the aforementioned issues in performance evaluation and help managers determine performance quality more easily. The joint confidence interval of the two indices serves as the feasible region, and we used linear programming to solve the upper confidence limit of the discriminant index, then performed statistical hypothesis testing using this upper confidence limit to determine whether a service item falls within the “needs improvement” zone. Finally, we present a case study to demonstrate the applicability of the proposed model by assessing a computer-assisted language learning (CALL) system.