Cross-Modal Adaptive Feedback Knowledge Distillation for Enhanced sEMG-Based Semantic Recognition
Big Data and Cognitive Computing · 28.10.2026 · 10 (11) · 368
DOI: 10.3390/bdcc10110368 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 28.10.2026. Verfasst von Junfeng Wei und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Guangxi Minzu University Talent Introduction Research Startup Projec, The 2026 Guangxi Marine Economy Talent Support Special Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
In semantic recognition based on surface electromyography (sEMG), low signal-to-noise ratios and physiological differences across subjects limit the ability of unimodal sEMG features to fully represent speech semantics, constraining recognition accuracy. Existing multimodal fusion methods can improve accuracy but often require large models and high computational complexity. Mismatches in feature spaces and learning capacity between multimodal teachers and unimodal students further limit cross-modal knowledge transfer. To address these issues, this paper proposed cross-modal adaptive feedback knowledge distillation (CAFKD). The multimodal teacher model uses Bi-GRU to fuse temporal features from synchronously acquired audio, lip image sequences, and sEMG signals, generating high-level representations that encode complementary semantic information. This multimodal knowledge was transferred to an sEMG-only student through a joint loss combining classification, output distribution distillation, and intermediate feature distillation. In addition, the cross-modal adaptive feedback mechanism (CAF) periodically adjusted the teacher using stagewise output feedback from a temporary student, enabling teacher guidance to better match the student’s learning state. In subject-independent evaluation on the AVE-Speech dataset, CAFKD achieved 78.13% accuracy on the 101-class closed-set short-utterance classification task, exceeding the unimodal Bi-GRU baseline by 4.82 percentage points. Ablation experiments showed that adding intermediate feature distillation to output distribution distillation increased test accuracy by 1.49 percentage points. CAF further improved accuracy by 1.46 percentage points over joint distillation. The student model also retains the same parameter count and FLOPs as the Bi-GRU baseline, at 4.42 M and 0.29 G, respectively. These results indicate that CAFKD improves recognition performance on unseen subjects while preserving a lightweight architecture for sEMG-only inference.
Förderung
- The Guangxi Minzu University Talent Introduction Research Startup Projec
- The 2026 Guangxi Marine Economy Talent Support Special Program
- National Natural Science Foundation of China
- the Guangxi Natural Science Foundation Project
Zitieren
APA
Wei, J., Ruan, G., Jing, P., & Li, Y. (2026). Cross-Modal Adaptive Feedback Knowledge Distillation for Enhanced sEMG-Based Semantic Recognition. Big Data and Cognitive Computing, 10(11), 368. https://doi.org/10.3390/bdcc10110368
Vancouver
Wei J, Ruan G, Jing P, Li Y. Cross-Modal Adaptive Feedback Knowledge Distillation for Enhanced sEMG-Based Semantic Recognition. Big Data and Cognitive Computing. 2026;10(11):368. doi:10.3390/bdcc10110368
BibTeX
@article{Wei2026,
author = {Wei, Junfeng and Ruan, Guihong and Jing, Peiguang and Li, Yun},
title = {Cross-Modal Adaptive Feedback Knowledge Distillation for Enhanced sEMG-Based Semantic Recognition},
journal = {Big Data and Cognitive Computing},
year = {2026},
volume = {10},
number = {11},
pages = {368},
doi = {10.3390/bdcc10110368}
}
EUVIMED