Four-layer system architecture for intelligent oral diagnosis and adaptive training¶

Element · All elements
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description¶

The proposed system is organized as a hierarchical four-layer architecture: Data Acquisition, Feature Extraction, Intelligent Diagnosis, and Adaptive Training. "the Data Acquisition Layer acts as the system’s sensory interface: it handles audio capture, runs noise-reduction preprocessing, and applies voice activity detection to break continuous recordings into analysable speech segments." Layers communicate through standardized interfaces, with time-critical recognition and feedback running synchronously and computationally intensive diagnostic analysis and learner-model updates running asynchronously.

Design Implications¶

Context¶

Requirements¶

• Standardized interfaces between layers so heterogeneous feature vectors converge at the diagnosis layer before dimension-specific scoring

Constraints¶

• The design was chosen for modularity, maintainability, and differing compute demands of components, per the authors' practical rationale

Target Learners¶

• University students practicing spoken English

Target Learning Goals¶

• Oral proficiency diagnosis and personalized practice recommendation

Claims¶

• Over eight weeks, university learners receiving reinforcement learning-optimized oral practice sequencing attained normalized learning gains approximately 2.2 times higher than learners following fixed curricula [+M]
• A multi-task CNN-LSTM diagnostic model with attention-based fusion achieves correlations of 0.887, 0.862, 0.824, and 0.793 with human expert ratings across four oral proficiency dimensions under speaker-independent testing [+M]

Related Elements¶

Examples¶

-

Key Sources¶

• Chai Rui. (2026). Deep learning-based intelligent diagnosis and adaptive training system for university english oral proficiency. Scientific Reports. https://doi.org/10.1038/s41598-026-51608-6