The evaluation of pronunciation for spoken English is one of the key problems for computer aided spoken language learning. While the most of researchers focus on the improvement of speech recognition to build a reliable evaluation system, there still needs a model that fuses the reliabilities of existing speech processing systems and the learner personalities into the evaluation system. In this paper, the Sugeno integral techniques are introduced to solve this problem. At first, the English phonemes that are hard to be distinguished (HDP) from Chinese language learner are collected and are grouped into different HDP sets. Then, the system reliabilities for distinguishing the phonemes within a HDP set are computed based on the standard speech corpus and are integrated with the phoneme recognition results under the Sugeno integral framework. The fuzzy measures are given for each subset of speech segments that contains at least 10 occurrences of phonemes within a same HDP set. Finally, the linguistic evaluation results are given by the Sugeno integral model based on system reliability and fuzzy measures. The experiment taken on Sphinx-4 shows that, under the 84.7% average recognition rate of the system, our pronunciation evaluation model get reliable and stable results for 3 test corpora.

No abstract

Many experts and scholars focus on the Maclaurin symmetric mean (MSM) operator, which can reflect the interrelationship among the multi-input arguments. It has been generalized to different fuzzy environments and put into use in various actual decision problems. The fuzzy number intuitionistic fuzzy numbers (FNIFNs) could well depict the uncertainties and fuzziness during the English teaching quality evaluation. And the English teaching quality evaluation is frequently viewed as the multiple attribute decision-making (MADM) issue. We expand the MSM equation with FNIFNs to propose the fuzzy number intuitionistic fuzzy MSM (FNIFMSM) equation and fuzzy number intuitionistic fuzzy weighted MSM (FNIFWMSM) equation in this study. A few MADM tools are developed with FNIFWMSM equation. Finally, taking English teaching quality evaluation as an example, this paper illustrates the depicted approach.

The English classroom teaching effect evaluation is looked as the multiattribute group decision-making (MAGDM). Thus, a useful MAGDM algorithm is needed to cope with it. Depending on the classical GRA process and interval-valued IFSs (IVIFSs), this study builds the IVIF-GRA process to assess the English classroom teaching effect. First of all, the concepts of IVIFSs are reviewed. In addition, the weights of criteria are derived through the CRITIC method. Afterwards, the GRA model is extended to IVIFSs to get the final result of the alternative. Therefore, all alternatives could be ranked and the optimal one with English classroom teaching effect can be identified. At last, a given numerical example and some given comparative studies are obtained. The analysis results show that the defined algorithms are effective for solving the English classroom teaching effect evaluation.

No abstract