A Spoken English Teaching System Based on Speech Recognition and Machine Learning

Fengming Jiao,Ping Zhao,Jiao Song,Xin Zhao,Ru Wang

doi:10.3991/ijet.v16i14.24049

Abstract

The learning model and environment are two major constraints on spoken English learning by Chinese learners. The maturity of computer-aided language learning brings a new opportunity to spoken English learners. Based on speech recognition and machine learning, this paper designs a spoken English teaching system, and determines the overall architecture and functional modules of the system according to the system’s functional demand. Specifically, MATLAB was adopted to realize speech recognition, and generate a speech recognition module. Combined with machine learning algorithm, a deep belief network (DBN)-support vector machine (SVM) model was proposed to classify and detect the errors in pronunciation; the module also scores the quality and corrects the errors in pronunciation. This model was extended to a speech evaluation module was created. Next, several experiments were carried out to test multiple attributes of the system, including the accuracy of pronunciation classification and error detection, recognition rates of different environments and vocabularies, and the real-timeliness of recognition. The results show that our system achieved good performance, realized the preset design goals, and satisfied the user demand. This research provides an important theoretical and practical reference to transforming English teaching method, and improving the spoken English of learners.

Highlights

With the gradual acceleration of the economic globalization, English, as an international language, has become an important tool in people’s communication
Functional modules of the system: Figure 3 shows the functional modules of the spoken English teaching system
With the requirement analysis and the overall design, a spoken English teaching system based on speech recognition and machine learning was established

Summary

Introduction

With the gradual acceleration of the economic globalization, English, as an international language, has become an important tool in people’s communication. Constrained by the learning model and the environment, most English learners in China find it very difficult to learn spoken English. When speaking English, students may not put their tongues in the right position due to the influence of their mother tongue, leading to inaccurate pronunciation [1]. Teachers often focus on teaching grammar and vocabulary in English classes and tend to overlook students’ pronunciation. Even though greater importance has been attached to spoken English teaching, due to the limited class time, teachers find it difficult to give one-to-one tutoring to students, and learners do not know what pronunciation problems they have and how to correct them. It is quite challenging for students to improve their spoken English

Methods

Results

Conclusion