Pronunciation Training Research Articles

SELECTION OF DISCRIMINATIVE FEATURES FOR ARABIC PHONEME’S MISPRONUNCIATION DETECTION

Pronunciation training is an important part of Computer Assisted Pronunciation Training (CAPT) systems. Mispronunciation detection systems recognized pronunciation mistakes from user’s speech and provided them feedback about their pronunciation. Acoustic phonetic features plays a vital role in speech classification based applications. This research work investigated the suitability of various acoustic features: pitch, energy, spectrum flux, zero-crossing, Entropy and MelFrequency Cepstral Coefficients (MFCCs). Sequential Forward Selection (SFS) was used to find out most suitable acoustic features from the computed feature set. This study used K-Nearest Neighbors (K-NN) classifier was used to detect the pronunciation mistakes from Arabic phonemes. This research selected the set of most discriminative acoustic features for each phoneme. K-NN achieved accuracy of 92.15% for mispronunciation detection of Arabic Phonemes.

SELECTION OF DISCRIMINATIVE FEATURES FOR ARABIC PHONEME’S MISPRONUNCIATION DETECTION

Pronunciation training is an important part of Computer Assisted Pronunciation Training (CAPT) systems. Mispronunciation detection systems recognized pronunciation mistakes from user’s speech and provided them feedback about their pronunciation. Acoustic phonetic features plays a vital role in speech classification based applications. This research work investigated the suitability of various acoustic features: pitch, energy, spectrum flux, zero-crossing, Entropy and MelFrequency Cepstral Coefficients (MFCCs). Sequential Forward Selection (SFS) was used to find out most suitable acoustic features from the computed feature set. This study used K-Nearest Neighbors (K-NN) classifier was used to detect the pronunciation mistakes from Arabic phonemes. This research selected the set of most discriminative acoustic features for each phoneme. K-NN achieved accuracy of 92.15% for mispronunciation detection of Arabic Phonemes

Dance and Language in Phonetics Class

The chapter focuses on specialized communication and, more exactly, the use of technical terms between laypersons and experts of dancing. The phonetics of German is regarded as a resource for conveying specialist knowledge via the speech organs activated in the articulation of sounds, vowel quantity and quality during pronunciation training. Using material from a series of workshops, it can be demonstrated how the learner - the contemporary dancer - relates the specialist knowledge from the field of German phonetics to the specialist knowledge about the qualities of movement, and how s/he includes body movement in the pronunciation training which becomes a performative practice.

Thinking about the Way of English Pronunciation Training Penetrating into English Speech Training

Thinking about the Way of English Pronunciation Training Penetrating into English Speech Training

Explore the Innovative Path of English Speech Pronunciation Training

The development trend of global economic integration makes the trade between countries more and more close. English, the world language, occupies an increasingly important position in international exchanges and cultural and economic activities, and the oral English ability is gradually valued by educators. English speech can effectively stimulate the motivation of English learning and improve speakers' English level from multiple perspectives. Therefore, in order to further enhance the appeal of English speech, apart from the careful writing of English speech content, speech speech and other on-the-spot performance is also an important factor affecting the effect of English speech. Based on this, this paper puts forward some innovative ways of English speech pronunciation training, hoping to help speakers implement the art of speech, make full use of pronunciation and posture to infect the audience, achieve the purpose of English speech, and deepen their own English literacy.

The Effect of Turkish Pronunciation Training on Brain: An fMRI Study

This study aimed to develop the pronunciation skills of students who learned Turkish as a foreign language and determine the extent of the instruction given for that purpose by observing its cognitive effects. It was designed as an in-class action research and carried out with nine students speaking different languages. Of those, five were bilinguals: Four were native speakers of their native tribal language and French, and one was a native speaker of Kazakh and Russian. The remaining four students were native speakers of Arabic. The fMRI findings at the beginning and the end of the study showed that phonological and reading motor processes were better for bilingual learners who were native tribal speakers and learned French and Mongolian as their country's official language, compared with native Arabic monolingual learners. Based on the analysis, it can be stated that an increase in foreign language sound awareness of learners results in the acquisition of more accurate pronunciation skills.

Synchronous computer-mediated communication in pronunciation teaching: A survey study

Remote learning has been in the spotlight since the emergence of the coronavirus pandemic, notably boosting the development of distance learning in the last two years; as universities were obliged to close worldwide and lecturers had to teach online during lockdown, the use of Synchronous Computer-Mediated Communication (SCMC) started to prevail. Pronunciation instruction was not an exception. Indeed, in-person lectures had used technology to support face-to-face (F2F) education by using videos and articles in class. However, educators had to adapt rapidly to teach through video-based platforms. Although much investigation has been conducted on Computer-Assisted Pronunciation Training (CAPT), and researchers currently show more and more interest in the use of new technologies within the pronunciation classroom, little research has been done regarding the teaching methodologies applied in teacher-guided online pronunciation instruction.

Polish learners’ self-assessment and reflections on their pronunciation progress

The aim of this pilot study is to describe, analyse and interpret the outcome of a pronunciation self-assessment task carried out by Polish learners of English at an academic level and their reflections on progress and what they believe they need in order to feel more successful as speakers of English in terms of pronunciation. It also attempts to discuss certain individual factors determining the perceptions of the learners’ performance. Seventeen Polish first-year university students of English philology were asked to assess their improvement in the production of individual English sounds based on two recording sessions that they had undergone at the beginning and at the end of the academic year, i.e. before and after a two-semester pronunciation course. The results of the students’ assessment were then compared with the teacher’s assessment. All of the participants were recorded reading a diagnostic passage which concentrates on examining individual segments of Standard British English (SBE). They were also asked a number of questions in the form of an open-ended questionnaire related to their attitudes and feelings towards certain mispronunciations and general performance in the two recording sessions, how they perceive the way they speak English, their opinions as to the most effective techniques and activities in pronunciation training.

Effects of imitation and self-imitation practice on L2 pronunciation progress

AbstractThe major aim of the current study is to verify whether an interdependence between self-imitation practice and L2 pronunciation improvement in the process of second-language acquisition is stronger than traditional imitation tasks. 35 Polish students of Applied Linguistics (at English level B2+) divided into two groups performed imitation and self-imitation exercises in order to improve their L2 pronunciation skills. Three acoustic parameters were considered, namely, articulation rate, speech rate and average syllable duration. The results of the research have revealed that there is a significant interdependence between L2 pronunciation improvement and self-imitation training in terms of speech rate. The outcomes of the research are in line with Ding et al. (2019), De Meo et al.’s (2013), and Felps et al.’s (2009) assertion that the better the match between learners’ voices and their modified equivalents, the more positive impact there is on L2 pronunciation training.

METHODS OF IMPLEMENTING THE COMMUNICATIVE-ACTIVITY APPROACH UNDER CONDITIONS OF DISTANCE LEARNING OF A FOREIGN LANGUAGE

The article deals with theoretical fundamentals of the communicative-activity approach to mastering foreign languages as well as methods of its implementation under conditions of distance learning. Authors of the publication share the practical experience of distance work with freshmen of the Zhytomyr Polytechnic State University, foreign students studying the Ukrainian language. The publication considers problems that arise at the initial stage of learning a foreign language regardless of the language studied. The particular importance is attached to the following issues: the language divide, its types, reasons of its occurrence and ways to overcome it; typical mistakes made by students in the process of distance learning of reading and writing, as well as ways and methods for their prevention and elimination; the methodology for pronunciation training. The authors of the article tend to consider the usage of podcasts, mental maps and communicatively oriented authentic textbooks to be the most effective methods of distance work.
 The article provides the description of textbooks which are focused on the communicative-activity approach to the language learning and enable to essentially achieve the educational goal during the distance learning process. The publication emphasizes that of the four types of speech activity - speaking, writing, reading, listening – reaching the first one is especially challenging in the distance learning process. The joint use of exercises from the textbook and the students’ involvement in real speech situations is successful for developing speaking skills. The authors propose patterns of real speech situations, describe their content and methodology of their application. They also vividly prove the effectiveness of using podcasts, mental maps, and authentic textbooks in the language learning process.

Use of ASR-Equipped Software in the Teaching of Suprasegmental Features of Pronunciation

Technology has paved the way for new modalities in language learning, teaching, and assessment. However, there is still a great deal of work to be done to develop such tools for oral communication, specifically tools that address suprasegmental features in pronunciation instruction. Therefore, this critical literature review examines how researchers have tried to create computer-assisted pronunciation training tools using automatic speech recognition (ASR) systems to aid language learners in the perception and production of suprasegmental features. We used 30 texts from 1990 to 2020 to explore how technologies have been and are currently being used to help learners develop their proficiency with suprasegmental features. Based on our thematic analysis, a persistent gap still exists between ASR-equipped software available to participants in research studies and what is available to university and classroom teachers and students. Additionally, there seems to be more development in the production of speech software for language assessment. In contrast, the translation of these tools into instructional tools for individualized learning seems to be almost non-existent. Moving forward, we recommend that more commercialized pronunciation systems utilizing ASR should be made publicly available using the technologies that are currently developed or are in development for the purposes of oral proficiency judgments.

Perception and production training effects on production of English lexical schwa by young Spanish learners

Abstract Phonetic training has been found to expedite aural and oral abilities in the L2. While considerable research has been conducted on the effects of perception training on production and of production training on perception, fewer studies have addressed them as separate training regimes in the same experimental setting outside laboratory conditions. This paper examined the effects of two training procedures (one based on production tasks and one based on perception tasks) on the production of English lexical schwa by young Spanish learners in their intact EFL classrooms. Both trained groups exhibited significant gains in the post-test and a slight advantage of the production-based trained group was observed. Learners’ orosensory awareness, self-perception, and self-feedback were actions included in this protocol which may have contributed to such advantage. Our results demonstrate that guided pronunciation training protocols can be successful in the classroom with young learners to boost production skills.

Leveraging audible and inaudible signals for pronunciation training by sensing articulation through a smartphone

• Under pronunciation principles, this paper presents a smartphone-based pronunciation training system for practicing monophthong regarding vowel articulation. • Speech and ultrasonic signals are captured and analyzed simultaneously to determine the tongue position and shape of the lips respecting uttering vowels. • The proposed system implementing a commercial smartphone is robust with high accuracy for practical scenarios. • The evaluation for its impact on user experience shows that the proposed system has raised learning engagement and enjoyment. Learning a foreign language pronunciation is the most challenging task for non-native speakers. Improving pronunciation based on feedback on pronunciation error scores is also not easy for learners. Our goal is to develop an alternative approach to pronunciation training that can point out articulation errors at the phoneme level to users through a smartphone-based system. Using self-correction as a means of ensuring learners' engagement, we focus on self-correction of pronunciation by adjusting articulation. In order to identify articulation concerning pronunciation, the system evaluates both audible and inaudible acoustic signals to examine fine-grained frequency-shifting direction of mouth movements and tongue position simultaneously. The result shows that the system can reach an average accuracy of 99.09% and is robust in different scenarios and genders. Additionally, the evaluation of the user study reveals that the proposed system provides positive user experiences and allows learners to improve their pronunciation more efficiently.

Using mobile applications with augmented reality elements in the self-study process of prospective translators

The paper deals with the use of mobile applications for language learning in the self-study process of prospective translators. A comparative analysis was made of some mobile language learning applications. The capabilities of mobile language learning applications are summarised, which include learning vocabulary grammar, pronunciation training, and practice listening and speaking. Particular attention is paid to interactive tasks and gamification of learning. An experiment was conducted with students using the Duolingo mobile app. The advantages of using mobile applications with augmented reality elements in the self-study process of future translators are identified. The main ones are interactivity, accessibility, individual schedules, and the ability to learn anytime, anywhere. There has been a significant increase in motivation to learn a foreign language independently thanks to mobile apps. It is proposed that mobile applications should only be seen as additional opportunities for independent and autonomous learning.

Learning challenging L2 sounds via computer‐assisted training: Audiovisual training with an airflow model

AbstractBackgroundTeaching Mandarin as a second language (L2) has become an important profession and an important research area. The acquisition of unaspirated and aspirated consonants in Mandarin has been reported to be rather challenging for L2 learners.ObjectivesIn the current study, a 3‐D airflow model was integrated into the virtual talking head for audiovisual pronunciation training in these Mandarin consonants.MethodsUsing the eye‐tracking technique, Experiment 1 investigated L2 learners' general acceptance and gauged attention distribution online while learning with the system. To further compare training efficacy, learning outcomes were evaluated by randomly dividing Japanese learners of Mandarin into different training groups using the 3‐D tutor with and without an airflow model, respectively, in Experiment 2.Results and ConclusionsEye‐tracking results showed that the talking head was well accepted, and was successful in directing L2 learners' attention to the visual modality of the airflow model marking the contrast in aspiration. Furthermore, the additional visual cue of the airflow model helped enhance their production of the aspirated Mandarin stops. Moreover, this computer‐assisted training approach was shown to be robust as the advantage of training with an airflow model can be generalized to novel syllables with a change of tones or rimes.

Mispronunciation Detection and Diagnosis with Articulatory-Level Feedback Generation for Non-Native Arabic Speech

A high-performance versatile computer-assisted pronunciation training (CAPT) system that provides the learner immediate feedback as to whether their pronunciation is correct is very helpful in learning correct pronunciation and allows learners to practice this at any time and with unlimited repetitions, without the presence of an instructor. In this paper, we propose deep learning-based techniques to build a high-performance versatile CAPT system for mispronunciation detection and diagnosis (MDD) and articulatory feedback generation for non-native Arabic learners. The proposed system can locate the error in pronunciation, recognize the mispronounced phonemes, and detect the corresponding articulatory features (AFs), not only in words but even in sentences. We formulate the recognition of phonemes and corresponding AFs as a multi-label object recognition problem, where the objects are the phonemes and their AFs in a spectral image. Moreover, we investigate the use of cutting-edge neural text-to-speech (TTS) technology to generate a new corpus of high-quality speech from predefined text that has the most common substitution errors among Arabic learners. The proposed model and its various enhanced versions achieved excellent results. We compared the performance of the different proposed models with the state-of-the-art end-to-end technique of MDD, and our system had a better performance. In addition, we proposed using fusion between the proposed model and the end-to-end model and obtained a better performance. Our best model achieved a 3.83% phoneme error rate (PER) in the phoneme recognition task, a 70.53% F1-score in the MDD task, and a detection error rate (DER) of 2.6% for the AF detection task.

An Acoustic Feature-Based Deep Learning Model for Automatic Thai Vowel Pronunciation Recognition

For Thai vowel pronunciation, it is very important to know that when mispronunciation occurs, the meanings of words change completely. Thus, effective and standardized practice is essential to pronouncing words correctly as a native speaker. Since the COVID-19 pandemic, online learning has become increasingly popular. For example, an online pronunciation application system was introduced that has virtual teachers and an intelligent process of evaluating students that is similar to standardized training by a teacher in a real classroom. This research presents an online automatic computer-assisted pronunciation training (CAPT) using deep learning to recognize Thai vowels in speech. The automatic CAPT is developed to solve the inadequacy of instruction specialists and the complex vowel teaching process. It is a unique system that develops computer techniques integrated with linguistic theory. The deep learning model is the most significant part of recognizing vowels pronounced for the automatic CAPT. The major challenge in Thai vowel recognition is the correct identification of Thai vowels when spoken in real-world situations. A convolutional neural network (CNN), a deep learning model, is applied and developed in the classification of pronounced Thai vowels. A new dataset for Thai vowels was designed, collected, and examined by linguists. The result of an optimal CNN model with Mel spectrogram (MS) achieves the highest accuracy of 98.61%, compared with Mel frequency cepstral coefficients (MFCC) with the baseline long short-term memory (LSTM) model and MS with the baseline LSTM model have an accuracy of 94.44% and 90.00% respectively.

Computer-assisted pronunciation training—Speech synthesis is almost all you need

The research community has long studied computer-assisted pronunciation training (CAPT) methods in non-native speech. Researchers focused on studying various model architectures, such as Bayesian networks and deep learning methods, as well as on the analysis of different representations of the speech signal. Despite significant progress in recent years, existing CAPT methods are not able to detect pronunciation errors with high accuracy (only 60% precision at 40%–80% recall). One of the key problems is the low availability of mispronounced speech that is needed for the reliable training of pronunciation error detection models. If we had a generative model that could mimic non-native speech and produce any amount of training data, then the task of detecting pronunciation errors would be much easier. We present three innovative techniques based on phoneme-to-phoneme (P2P), text-to-speech (T2S) and speech-to-speech (S2S) conversion to generate correctly pronounced and mispronounced synthetic speech. We show that these techniques not only improve the accuracy of three machine learning models for detecting pronunciation errors, but also help establish a new state-of-the-art in the field. Earlier studies have used simple speech generation techniques such as P2P conversion, but only as an additional mechanism to improve the accuracy of pronunciation error detection. We, on the other hand, consider speech generation to be the first-class method of detecting pronunciation errors. The effectiveness of these techniques is assessed in the tasks of detecting pronunciation and lexical stress errors. Non-native English speech corpora of German, Italian, and Polish speakers are used in the evaluations. The best proposed S2S technique improves the accuracy of detecting pronunciation errors in AUC metric by 41% from 0.528 to 0.749 compared to the state-of-the-art approach.

The Modular Design of an English Pronunciation Level Evaluation System Based on Machine Learning

To improve the accuracy of English pronunciation level evaluation, we study the modularization of the English pronunciation level evaluation system unfolding based on machine learning. The S3C2440A chip is used as the main processor of the system, and the spoken English recordings are sent to the evaluation module through the speech upload module. In the evaluation module, the pronunciation signal is filtered by the multilayer wavelet feature scale transformation method, and the intonation, speed, pitch, rhythm, and emotion features are decomposed and extracted. The test results show that the misjudgment rate of different mispronunciations is less than 1% when the system is used to evaluate the English pronunciation level, which proves that it has high evaluation accuracy. In-depth study of speech recognition related theories, speech scoring, and pronunciation correction algorithms are discussed, and an assisted learning system based on AP scoring method and pronunciation resonance peak comparison technology is proposed for the problem of inaccurate pronunciation scoring and lack of effective feedback of speech recognition technology applied to oral learning. The English pronunciation training system has achieved the expected pronunciation following of English phonetic symbols and words, real-time pronunciation. The English pronunciation training system has achieved all basic functions such as pronunciation following, real-time pronunciation evaluation, and pronunciation correction of English phonemes and works as expected. After testing, the system has achieved high accuracy in pronunciation scoring, and the similarity with experts’ scoring is over 90% for vowel and word pronunciation; the efficiency of pronunciation correction reaches 80%, which can improve learners’ pronunciation level to a certain extent.

Do beliefs matter? The relationship between beliefs about peer feedback and peer feedback outcomes on pronunciation

This study investigated the relationship between learner beliefs about peer feedback and development of second language (L2) pronunciation skills after peer feedback on pronunciation had been used in the classroom. Seventy-four first-year learners of German were assigned to a peer feedback provider group, a peer feedback receiver group, and a control group. After completing a questionnaire designed to elicit learner beliefs about peer feedback, the provider group and the receiver group received general pronunciation training. Following the training, the provider group gave feedback to peers on their pronunciation and the receiver group listened to this feedback. Participants’ learning gains were measured by means of native speaker comprehensibility ratings of their productions both before and after the intervention. Statistical analyses revealed significant, positive relationships between learner beliefs about peer feedback and their learning gains. These results suggest that learners who held more positive beliefs about peer feedback tended to improve more after peer feedback had been implemented into their classroom. Pedagogical implications of these findings are discussed.