English Listening Teaching Mode under Artificial Intelligence Speech Synthesis Technology

Author:

Yu Cui1ORCID,Wu Lili1ORCID,Li Junyan1ORCID,Li Shuang2ORCID

Affiliation:

1. Department of General Foreign Languages, Changchun University of Finance and Economics, Changchun 130122, Jilin, China

2. College of Information Engineering, Changchun University of Finance and Economics, Changchun 130122, Jilin, China

Abstract

To discuss the application of artificial intelligence (AI) speech synthesis technology and wireless network technology in English listening teaching, firstly, the present situation of English listening teaching is analyzed. Secondly, a questionnaire is designed to investigate the feasibility of AI speech synthesis technology in English listening teaching. Finally, the control group (a traditional mode of English listening teaching) and experimental group (AI speech synthesis technology) are set up, compared, and analyzed. The survey shows that for natural fluency, speech synthesis has the lowest score. The textbook audio score is the highest, with an average score of 4.23. According to the mean opinion score (MOS), the AI speech synthesis technology belongs to high-quality speech coding. Therefore, the English audio generated by combining AI speech synthesis technology under wireless network technology also has high quality. Meanwhile, 113 people in the survey consider that the clear articulation of the synthesized audio is full marks, which is clearer than the English audio matching the textbook, indicating that students think the English audio of the supporting textbook is poor in the clear articulation, which affects students’ listening. Moreover, the English listening scores of the experimental group are notably better than those of the control group. It is hoped that the traditional teaching mode can be better integrated with wireless networks and AI technology, thereby improving the clarity of English listening, providing mobile learning, and advancing students' English performance and learning efficiency.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Reference30 articles.

1. M. S. Al-Radhi , O. Abdo , T. G. Csapo , , “ A continuous vocoder for statistical parametric speech synthesis and its evaluation using an audio-visual phonetically annotated Arabic corpus ,” Computer speech and language , vol. 60 , no. 2, pp. 101025.1-101025.15, 2020. M. S. Al-Radhi, O. Abdo, T. G. Csapo, et al., “A continuous vocoder for statistical parametric speech synthesis and its evaluation using an audio-visual phonetically annotated Arabic corpus,” Computer speech and language, vol. 60, no. 2, pp. 101025.1-101025.15, 2020.

2. Gated Recurrent Attention for Multi-Style Speech Synthesis

3. English speech sound improvement system based on deep learning from signal processing to semantic recognition;Yang Y.;International Journal of Speech Technology,2020

4. Analysis of English Listening Obstacles Based on Computer Assisted Instruction;Li H.;Computer-Aided Design and Adoptions,2021

5. Evaluating intelligent personal assistants for L2 listening and speaking development;Dizon G.;Language, Learning and Technology,2020

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3