Optional English Speech Teaching Method Based on Recognition Emotion Mining and Deep Learning Algorithms

Authors

  • Xinyu Zhang Cangzhou Normal University, Cangzhou, Hebei 061000, China
  • Hui Li Cangzhou Normal University, Cangzhou, Hebei 061000, China
  • Na Wang Cangzhou Normal University, Cangzhou, Hebei 061000, China
  • Ruilin Shi Cangzhou Normal University, Cangzhou, Hebei 061000, China

Abstract

Speech recognition technology and speech evaluation technology is the core of computer-aided speech learning. Of the two, speech recognition technology is particularly critical and plays a vital role. This paper analyses the application of emotion mining and deep learning algorithms in the recognition and teaching of English speech. Emotional visualization can enable teachers and curriculum managers to be more intuitive when sensing emotional changes in students’ learning process, and will assist teachers to provide personalized teaching and intervention. The experimental results show that the model presented in this paper for English phonetics teaching, speech recognition and evaluation is reasonable and valid. It can give learners timely, accurate and objective evaluation and feedback guidance, and can help learners identify the differences between their own pronunciation and the standard pronunciation. In addition, this paper optimizes the English language model by means of the sub-word modeling
method, which alleviates the problem of sparseness and robustness of the traditional whole-word language model brought by the very large vocabulary of adhesive words.

Keywords: Speech recognition; Deep learning; Emotion mining; DNN algorithm

Cite As

X. Zhang, H. Li, N. Wang, R. Shi, "Optional English Speech Teaching Method Based on Recognition
Emotion Mining and Deep Learning Algorithms", Engineering Intelligent Systems, vol. 27
no. 3, pp. 141-150, 2019.




Downloads

Published

2019-09-01

Issue

Vol. 27 No. 3 (2019): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.