Human-machine interfaces and wearable electronics, as fundamentals to achieve human-machine interactions, are becoming increasingly essential in the era of the Internet of Things. However, contemporary wearable sensors based on resistive and capacitive mechanisms demand an external power, impeding them from extensive and diverse deployment. Herein, a smart wearable system is developed encompassing five arch-structured self-powered triboelectric sensors, a five-channel data acquisition unit to collect finger bending signals, and an artificial intelligence (AI) methodology, specifically a long short-term memory (LSTM) network, to recognize signal patterns. A slider-crank mechanism that precisely controls the bending angle is designed to quantitively assess the sensor's performance. Thirty signal patterns of sign language of each letter are collected and analyzed after the environment noise and cross-talks among different channels are reduced and removed, respectively, by leveraging low pass filters. Two LSTM models are trained using different training sets, and four indexes are introduced to evaluate their performance, achieving a recognition accuracy of 96.15%. This work demonstrates a novel integration of triboelectric sensors with AI for sign language recognition, paving a new application avenue of triboelectric sensors in wearable electronics.