Year: 2024
Type: conference-paper
Abstract: This article aims to explore and verify the effectiveness and practicability of the big data-driven oral English assessment model, so as to overcome the subjectivity and inefficiency of conventional assessment. By integrating big data (BD) processing and speech signal processing, this article constructs a multi-dimensional and automatic oral English assessment model. A large quantity of oral English data covering different learners' backgrounds is collected, and strict preprocessing and feature engineering are carried out. Then, the model is trained and optimized using advanced machine learning and deep learning algorithms. The results show that the proposed model has a highly consistent performance with manual scoring in multiple dimensions, including pronunciation accuracy, intonation naturalness, and language fluency, while also significantly improving assessment efficiency. It concludes that the BD-driven oral English assessment model is feasible and accurate in practical application.
Author: Tingting Liu
Institution: Yunnan Land and Resources Vocational College
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: gold
OpenAlex ID: W4412524693