With the development of artificial intelligence and intelligent sensor technologies, traditional legal English teaching approaches have faced numerous challenges in handling multimodal inputs and complex reasoning tasks. In response to these challenges, a cross-modal legal English question-answering system based on visual and acoustic sensor inputs was proposed, integrating image, text, and speech information and adopting a unified vision–language–speech encoding mechanism coupled with dynamic attention modeling to effectively enhance learners’ understanding and expressive abilities in legal contexts. The system exhibited superior performance across multiple experimental evaluations. In the assessment of question-answering accuracy, the proposed method achieved the best results across BLEU, ROUGE, Precision, Recall, and Accuracy, with an Accuracy of 0.87, Precision of 0.88, and Recall of 0.85, clearly outperforming the traditional ASR+SVM classifier, image-retrieval-based QA model, and unimodal BERT QA system. In the analysis of multimodal matching performance, the proposed method achieved optimal results in Matching Accuracy, Recall@1, Recall@5, and MRR, with a Matching Accuracy of 0.85, surpassing mainstream cross-modal models such as VisualBERT, LXMERT, and CLIP. The user study further verified the system’s practical effectiveness in real teaching environments, with learners’ understanding improvement reaching 0.78, expression improvement reaching 0.75, and satisfaction score reaching 0.88, significantly outperforming traditional teaching methods and unimodal systems. The experimental results fully demonstrate that the proposed cross-modal legal English question-answering system not only exhibits significant advantages in multimodal feature alignment and deep reasoning modeling but also shows substantial potential in enhancing learners’ comprehensive capabilities and learning experiences.

This study developed an automated language learning teaching assessment system based on electroencephalography (EEG) and differential language large models (LLMs), aimed at enhancing language instruction effectiveness by monitoring learners’ cognitive states in real time and personalizing teaching content accordingly. Through detailed experimental design, the paper validated the system’s application in various teaching tasks. The results indicate that the system exhibited high precision, recall, and accuracy in teaching effectiveness tests. Specifically, the method integrating differential LLMs with the EEG fusion module achieved a precision of 0.96, recall of 0.95, accuracy of 0.96, and an F1-score of 0.95, outperforming other automated teaching models. Additionally, ablation experiments further confirmed the critical role of the EEG fusion module in enhancing teaching quality and accuracy, providing valuable data support and theoretical basis for future improvements in teaching methods and system design.

Multimodal perception for student-state monitoring is difficult to deploy in rural classrooms because sensors are noisy and computing resources are highly constrained. This work targets these challenges by enabling noise-resilient, multimodal, real-time student-state recognition on low-cost edge devices. We propose LightEdu-Net, a sensor-noise-adaptive Transformer-based multimodal network that integrates visual, physiological, and environmental signals in a unified lightweight architecture. The model incorporates three key components: a sensor noise adaptive module (SNAM) to suppress degraded sensor inputs, a cross-modal attention fusion module (CMAF) to capture complementary temporal dependencies across modalities, and an edge-aware knowledge distillation module (EAKD) to transfer knowledge from high-capacity teachers to an embedded-friendly student network. We construct a multimodal behavioral dataset from several rural schools and formulate student-state recognition as a multimodal classification task with explicit evaluation of noise robustness and edge deployability. Experiments show that LightEdu-Net achieves 92.4% accuracy with an F1-score of 91.4%, outperforming representative lightweight CNN and Transformer baselines. Under a noise level of 0.3, accuracy drops by only 1.1%, indicating strong robustness to sensor degradation. Deployment experiments further show that the model operates in real time on Jetson Nano with a latency of 42.8 ms (23.4 FPS) and maintains stable high accuracy on Raspberry Pi 4B and Intel NUC platforms. Beyond technical performance, the proposed system provides a low-cost and quantifiable mechanism for capturing fine-grained learning process indicators, offering new data support for educational economics studies on instructional efficiency and resource allocation in underdeveloped regions.

To address the limitations of low fusion efficiency and insufficient personalization in multimodal perception for educational intelligence, a novel deep learning framework is proposed that integrates image sensor data with textual and contextual information through a cross-modal attention mechanism. The architecture employs a cross-modal alignment module to achieve fine-grained semantic correspondence between visual features captured by image sensors and associated textual elements, followed by a personalized feedback generator that incorporates learner background and task context embeddings to produce adaptive educational guidance. A cognitive weakness highlighter is introduced to enhance the discriminability of task-relevant features, enabling explicit localization and interpretation of conceptual gaps. Experiments show the proposed method outperforms conventional fusion and unimodal baselines with 92.37% accuracy, 91.28% recall, and 90.84% precision. Cross-task and noise-robustness tests confirm its stability, while ablation studies highlight the fusion module’s +4.2% accuracy gain and the attention mechanism’s +3.8% recall and +3.5% precision improvements. These results establish the proposed method as a transferable, high-performance solution for next-generation adaptive learning systems, offering precise, explainable, and context-aware feedback grounded in advanced multimodal perception modeling.