Big Data Based English Oral Teaching by Voice Network Analysis in 6G Wireless Sensor Transmission Model

Wireless communication technology, especially 6G networks, has enabled new instructional methods. Developing technologies is essential in education for effective learning, especially in English language teaching. This method uses voice network analysis to improve teaching. Educators can acquire valuable insights into students’ pronunciation, fluency, intonation, and other language acquisition skills using the massive volumes of oral session data. This study proposed a 6G wireless sensor transmission concept that uses big data to inform oral English instruction using voice network analysis. Initially, we analysed the spoken English Digit dataset, available in UCI’s machine learning repository and gathered from the Automatic Signalling Laboratory at Badji-Mokhtar University. We prepossessed to standardise the data’s scale using min-max normalization, and features are extracted using adaptive linear discriminate analysis (A-LDA). Improved reparability across classes of these extracted features, capturing the original feature space’s most discriminative information. We proposed the scheduling joint optimised with deep neural network (SJO-DNN) for voice network analysis in a 6G wireless sensor transmission model using an oral English teacher. These algorithms were developed to improve student-teacher communication. This may involve assessing spoken interactions for clarity, coherence, and engagement. Findings indicate that the suggested approach exceeds existing approaches. This would make it possible to evaluate the proposed solution’s efficacy in terms of student’s performance rate, accuracy, execution time, false alarm rate (FAR) and scalability. To improve the data in the 6G wireless sensor transmission model, this proposes a way to evaluate big data-based oral English instruction using voice network analysis.