A 7.2 MB branched DNN, fed with MediaPipe landmarks encoded as 947 ASL parameter features, classifies 343 isolated American Sign Language signs with 92% video-level accuracy and sub-10 ms latency on edge devices.
KD-MSLRT: Lightweight Sign Language Recognition Model Based on Mediapipe and 3D to 1D Knowledge Distillation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for the 72 million hearing-impaired people worldwide. Sign language translation models, relying on video inputs, involves with large parameter sizes, making it time-consuming and computationally intensive to be deployed. This directly contributes to the scarcity of human-centered technology in this field. Additionally, the lack of datasets in sign language translation hampers research progress in this area. To address these, we first propose a cross-modal multi-knowledge distillation technique from 3D to 1D and a novel end-to-end pre-training text correction framework. Compared to other pre-trained models, our framework achieves significant advancements in correcting text output errors. Our model achieves a decrease in Word Error Rate (WER) of at least 1.4% on PHOENIX14 and PHOENIX14T datasets compared to the state-of-the-art CorrNet. Additionally, the TensorFlow Lite (TFLite) quantized model size is reduced to 12.93 MB, making it the smallest, fastest, and most accurate model to date. We have also collected and released extensive Chinese sign language datasets, and developed a specialized training vocabulary. To address the lack of research on data augmentation for landmark data, we have designed comparative experiments on various augmentation methods. Moreover, we performed a simulated deployment and prediction of our model on Intel platform CPUs and assessed the feasibility of deploying the model on other platforms.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Developing Lightweight DNN Models With Limited Data For Real-Time Sign Language Recognition
A 7.2 MB branched DNN, fed with MediaPipe landmarks encoded as 947 ASL parameter features, classifies 343 isolated American Sign Language signs with 92% video-level accuracy and sub-10 ms latency on edge devices.