Evaluation method for student reading assignment for oral practice

Abstract

The invention discloses an evaluation method for a student reading assignment for oral practice. The method includes that a first text model L1 which a specified text corresponds to is established by a language model, the first text model L1 is designed to be a second text model L2 with competitive capacity according to a confused vocabulary list and a confused pronunciation list which the specified text corresponds to, a speech file read by a user is acquired through a speech acquisition device, a sound track is revaluated to obtain a revaluated speech file, a speech recognizer is guided by the model L2 to recognize the revaluated file to obtain a recognized text, and comparison and judgment with confidence degree weighing are performed for the recognized text and the specified text. By means of the evaluation method for the student reading assignment for the oral practice, acquired speech file can be accurately and efficiently recognized and judged.

Description

technical field [0001] The invention relates to the field of phonetic homework evaluation, in particular to a method for judging a student's reading aloud homework used for oral practice. Background technique [0002] The primary school stage is the most critical period for children to lay a good language foundation. Due to the lack of self-consciousness of students, hidden homework such as reading aloud, reciting, and dictation needs to be completed under the supervision of parents, and not all parents can follow the quantity and quality of homework assigned by the teacher. It is required to complete the whole process of supervision tasks, which leads to the unsatisfactory completion effect of some students' language learning homework. [0003] Through computer means, it can automatically complete the supervision of students' reading and dictation, which reduces the dependence of students on the supervision of parents or teachers to complete their homework, and improves the...

AI Technical Summary

Problems solved by technology

[0004] However, existing evaluation methods based on speaker-specific texts, such as voice input methods and voice dialing, etc., on the one hand, have a huge model due to the large corpus (usually the model of the full corpus is about 2G or even larger), so It takes a long recognition time, which reduces the recognition speed and affects the customer's perception

On the other hand, in Chinese and English teaching, most of the attention is on the reading of key words, and the existing recognition technology often only uses a fixed method to distinguish words, and the modeling process for children and adults, It is not well normalized. When the user's vocal characteristics are obviously different, the vocal tract parameters often need to be retrained. This is shown in practical applications. The same recognizer needs to be trained separately with different types of people. It is also inappropriate to set a unified voice channel for children, because there are a small number of children in the upper grades who develop the vocal tract earlier than children of the same age.

Therefore, the existing technical methods cannot carry out accurate and efficient identification, thus causing inconvenience in use

Images