A Prototype System with Speech Recognition Function for Practicing Speaking English

The literature indicates that many Japanese students enrolled in English language classes do not use English outside of class. Therefore, we assume that speech recognition technology can help create opportunities to speak English. Although some speech recognition software is widely available, few studies have been conducted using a software with a speech recognition function to investigate how we should adapt this technology to various levels of foreign language learners including Japanese students. The authors therefore developed a prototype system with a speech recognition function to create opportunities for Japanese students practicing English. We tested the system in a pilot study with 17 Japanese university students.

During the test, students were asked to use the correct English word for an image displayed by the system. Students’ responses to the system were collected via a survey questionnaire. The pilot test indicated that most of the words were recognized accurately, and the students’ speech was correctly reflected by the system to a significant extent. In addition, 88% of the students expressed a positive attitude toward the system. These results suggest that speech recognition create opportunities for students to practice their English. In addition, the results suggest that we should consider the balance between the software’s recognition rate and students’ motivation for practicing English when using speech recognition software for language instruction.

The Effectiveness of Using Speech Recognition Software to Practice English Speaking

This study investigates the possibility of using speech recognition software to provide English-speaking opportunities for English language learners. We have been developing a prototype tool for Japanese students and incorporated Microsoft Windows’ speech recognition function to answer the following research questions: (1) How well is the students’ speech recognized? (2) To what extent are recognized sentences accurate in terms of grammar and pronunciation, and which words or parts of speech are not spoken accurately by the students? and (3) How should the speech recognition function best be incorporated into the tool to create more opportunities for students to speak English? To answer these questions, our experiment tested three target English sentences spoken by 103 Japanese university students.

Regarding the first question, the results indicate that over 70% of the spoken sentences matched the registered sentences. Even though these sentences were not necessarily spoken with complete accuracy in terms of grammar and pronunciation, the students’ speech itself was generally recognized, and the sentences fell within a list of registered sentences in the tool’s database. Regarding the second question, for the first target sentence, 72% of the spoken sentences were recognized as the target sentence by the tool with complete accuracy in terms of grammar and pronunciation, 80% for the second, and 33% for the third. From the results of all three target sentences, it was observed that the students did not pronounce distinctly between “fold” and “hold,” and between “flame” and “frame.” Regarding the third research question, our results indicate that it is possible, to a certain extent, to use a speech recognition function to create English-speaking opportunities by using a list of registered sentences and by limiting the length of the sentences that must be recognized.

Role of a Subjective Difficulty Rating in Using a System for Practicing English Speaking

We have been developing a system that checks and provides information about the words and sentences that learners use when they practice speaking English.

In this study, we investigated the role of a subjective difficulty rating to identify sentences that were problematic for the learners by using our system. In the experiment, 72 Japanese university students were provided with 47 Japanese sentences and their English translations in advance of review quizzes. We instructed them to practice speaking the English translations without looking at the text information. This system, then asked them to translate the Japanese sentences into English. Then a self-reflective questionnaire was administered and participants rated the difficulty of each sentence on a five-point Likert scale. The average difficulty ratings of the 31 sentences that were answered correctly by more than 80% of the students varied from 1.7 to 4.2. Even though most students answered the questions correctly, they did not regard all the correctly answered sentences as easy. The standard deviation scores of the difficulty ratings of each sentence varied from 0.9 to 1.4. The difficulty ratings of some sentences were different for individual students. These results suggest that a subjective difficulty rating could play a role in observing how students actually feel about the difficulty levels of the sentences in the system, and could identify their individual weaknesses. Incorporating this kind of subjective difficulty rating into the system could help generate useful information for selecting the sentences within the system that suit individual student needs.

A Prototype System for Practicing English Speaking

In this study, we developed a prototype system that helps students practice speaking English. When students speak English, they may have difficulty expressing their intentions in real time, even when they know the correct words and phrases. To think of the correct English terms smoothly, it is important that students use the language knowledge they have acquired. By using probable linguistic situations, our system attempts to check and provide information about the words and phrases learners can use. We conducted an experiment with 105 first-year Japanese university students to investigate the following research questions: (1) Does the prototype system run properly, provide questions, and save the log data as expected?; (2) When we check the learners’ answers in real time, how many evaluation items and evaluation levels are appropriate?; and (3) How should we display the results of the evaluation to ensure visual comprehension? Concerning the first question, the results of the experiment show that the system runs properly and saves the log data. For the second question, the results suggest that a few evaluation items and a few evaluation levels are preferable for checking the learners’ answers in real time. Results for the third question suggest that a color-coded table could help visually interpret the learners’ results. In this table, English sentences grouping probable linguistic situations are classified according to the percentage of the correct answers, such as less than 50%, 50–80%, and more than 80%.

A Study on a Method of Integrating AR Markers into a Foreign Language Learning System for Task-based Activities

In this paper, we investigate a method to integrate Augmented Reality (AR) into a foreign language learning environment for task-based activities. We accomplish that task by focusing mainly on two objectives. First, AR markers can be applied to integrate some objects into the language learning environment as learning materials. Second, movement of an AR-tagged object used in the activities can be recognized and tracked, based on the AR marker’s positional information. AR technology is the integration of digital information with the user’s environment in real time. AR uses the existing environment and overlays digital information on it. We developed a prototype tool with the AR markers, and conducted an experiment to investigate the objectives mentioned above. In the experiment, 22 university students participated in the activities with the prototype tool. Concerning the first objective, the results of the experiment suggest that the prototype tool is easy to use as learning materials. The tool with the AR markers shows the possibility of achieving task-based style activity objectives. Concerning the second objective, an AR-tagged object moved by the learner was successfully recognized and tracked by the system in the activities.

The results suggest that the AR marker’s positional information could help track the learner’s movement in the learning activities. It should be noted that the ability to track an AR marker sometimes suffers from the problems caused by the amount of light in the classroom. Evenly distributed light is preferable when trying to identifying and detecting AR markers.