Oral English Auxiliary Teaching System Based on Deep Learning

Abstract

In order to solve the problem of the oral English auxiliary teaching system, a research based on Deep Learning was proposed. Based on the theory of Deep Learning, the teaching mode of Deep Learning for college students built on information technology was investigated in the research. As for Shallow Strategy, the item “I think that the best way to pass the English examination is to keep high frequency words in mind” changed most significantly from 3.3 to 2.68. As for Deep Strategy, the most significant change was the item “It can be very interesting for almost all the oral English topics as long as you engage in it actively.” The value increased from 3.31 to 3.97, which was almost close to 4. From the comparison, it could be found that the students changed from memorizing English words mechanically and passively in order to pass the exam to engaging in the oral English situation actively to solve problems so as to obtain self-satisfaction. As a language, English can reflect a unique cultural heritage. It is different from Chinese culture, which can improve learners’ spiritual and cultural accomplishments subtly. In addition, we should try to solve problems with English logical thinking, which can train our critical thinking and oral expression ability, enhance our self-confidence, and improve our sense of self-efficacy. A design-based research paradigm was used in the research. Through the integrated use of information technology, it aimed at building out a deeply mixed teaching mode based on “Cloud Class and Offline Class.” A combination of quantitative and qualitative data collection methods was adopted to evaluate the practical effect. According to the experimental results, two rounds of mixed-mode iterative loop design were performed for the mixed teaching mode. In order to make it more operable, it was improved and perfected continuously.