Automatic Scoring of Spoken Language Based on Basic Deep Learning

Abstract

The oral English test in domestic universities requires teachers to modify a large number of candidates’ oral recordings. This is the work of using time repeatedly. Using the CALL system to realize the automation of conversation recording can reduce the burden of teachers’ work. Therefore, it is of great practical significance to develop an automatic and accurate scoring system for oral English. With the development of artificial intelligence, deep learning technology has been gradually applied in various fields. Similarly, in the application of oral scoring, deep learning technology makes the implementation of such a system possible. Based on the deep learning technology, this paper proposes an automatic scoring algorithm for spoken language and implements a detailed design and evaluation system. The system consists of two modules. The pronunciation standard of spoken pronunciation and the content of spoken pronunciation are scored, and the sum of these two scores is the final score. Finally, this paper uses 650 oral English recordings from a college English test to train the artificial neural network. Experimental results show that if the training data set is small, the BP network model can obtain better comprehensive evaluation performance.