Title: Algorithm research of spoken English assessment based on fuzzy measure and speech recognition technology
Authors: Dongbo Cao; Ying Guo
Addresses: Department of Public English Teaching, Shenyang Institute of Engineering, Shenyang Liaoning 110136, China ' School of Civil Engineering, Shenyang University, Shenyang Liaoning 110044, China
Abstract: At present, many speech recognition algorithms are difficult to effectively evaluate the fuzziness of the evaluation algorithm. Based on this, this dissertation uses the speech recognition technology based on fuzzy measure to evaluate the spoken English. In the study the fuzzy measure, based on the traditional algorithm, is used to evaluate the spoken English and different characteristic parameters are extracted to construct the corresponding evaluation model. Simultaneously, the pronunciation is evaluated through automatic learning rules. The English speaking assessment model based on fuzzy measure and speech recognition technology is constructed and validated. The research shows that compared with the traditional algorithms, the spoken language evaluation algorithm based on fuzzy measure and speech recognition technology has the incomparable superiority, and can provide a reference for the follow-up related research.
Keywords: fuzzy measure; speech recognition; spoken English; evaluation algorithm.
International Journal of Biometrics, 2020 Vol.12 No.1, pp.120 - 129
Received: 05 Jan 2019
Accepted: 29 Jan 2019
Published online: 26 Feb 2020 *