Applications of robust recognition technology in the foreign language speech assessment system. (23rd November 2020)

• Record Type: Journal Article
• Authors: Huang, Weibo; Lu, Jiejing; Liu, Jianghui
• Is Part Of: International journal of high performance systems architecture. Volume 9:Number 2/3(2020)
• Page Start: 87
• Page End: 96
• Publication Date: 2020-11-23
• Subjects: English speech assessment system -- noise conditions -- robust speech recognition -- feature compensation -- VTS -- Vector Taylor Series; Computer architecture -- Periodicals; Computer systems -- Periodicals; High performance computing -- Periodicals; 004.205
• Languages: English
• ISSNs: 1751-6528

Abstract

This study proposes an improved speech assessment algorithm and an improved English (as a foreign language in China) speech assessment system based on robust speech recognition to assess learners' English pronunciation more accurately in noisy environments. In this paper, the traditional assessment framework of English speech recognition system is studied by the literature analysis method and survey research method. At the same time, the principle of speech recognition and robust speech recognition are further studied. Furthermore, the speech assessment algorithm and the system based on the feature compensation algorithm of Vector Taylor Series (VTS) are developed. Finally, the developed system is analysed by perceptual assessment of speech quality (PESQ) and mean opinion score (MOS). The results show that the MOS of the improved English (as the foreign language) speech assessment system is higher and the recognition performance is better than that of the traditional system in the noise conditions.