دورية أكاديمية

Education of Recognition Training Combined with Hidden Markov Model to Explore English Speaking.

التفاصيل البيبلوغرافية
العنوان: Education of Recognition Training Combined with Hidden Markov Model to Explore English Speaking.
المؤلفون: Hui Li1 lihuicangzhou@163.com, Xinyu Zhang1 flw@caztc.edu.cn, Ran Cui1 zhangxin1408@163.com, Na Wang1 wangnacangzhou@163.com
المصدر: Computer-Aided Design & Applications. 2020 Special Issue, Vol. 17, p101-112. 12p.
مصطلحات موضوعية: *HUMAN-computer interaction, *NATURAL language processing, *AUTOMATIC speech recognition, ENGLISH language, ORAL communication, SPEECH, SPEECH perception
مستخلص: In order to study a better speech scoring mechanism to achieve a more accurate evaluation of the practitioner's spoken pronunciation, and better help the practitioner to find out the lack of oral pronunciation, this study studied HMM-based speaking training system. The system evaluates the learner's spoken pronunciation from the vocal segment, the super-sound segment and the perception domain of the speech signal and improves the correlation between the computer score and the expert manual score. Aiming at the difficulty of oral English teaching in current English teaching, this paper designed a spoken language training system based on automatic speech evaluation using advanced computer technology, network technology, natural language processing technology, speech processing technology and human-computer interaction technology, which can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]
Copyright of Computer-Aided Design & Applications is the property of Computer-Aided Design & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
قاعدة البيانات: Business Source Index
الوصف
تدمد:16864360
DOI:10.14733/cadaps.2020.S1.101-112