Deep Learning

The EarSAVAS Dataset: Enabling Subject-Aware Vocal Activity Sensing on Earables

Subject-aware vocal activity sensing on wearables, which specifically recognizes and monitors the wearer's distinct vocal activities, is essential in advancing personal health monitoring and enabling context-aware applications. While recent …

EarCough: Enabling Continuous Subject Cough Event Detection on Hearables

HearCough: Enabling continuous cough event detection on edge computing hearables

本研究首次在端智能降噪耳机上实现了咳嗽事件的连续监测,通过将自研的轻量级端到端深度学习模型部署在端智能降噪耳机芯片,仅额外消耗5.2mW功耗,在真实患者的日常生活情景下,实现2Hz的咳嗽事件连续识别,准确率达90.0%。F1分数达89.5%,为未来呼吸道连续健康监测提供新的解决方案。

StarFont: Enabling Font Completion Based on Few Shots Examples

Font design has become an essential part of multimedia. It has the ability to convey the mood and intention of the designer. However, creating a new font for Chinese characters takes a lot of e-ort because the language contains over 20 thousand …