题目： | Deep learning-empowered triboelectric acoustic textile for voice perception and intuitive generative AI-voice access on clothing |
作者： | Beibei Shao1,2,3#, Tai-Chen Wu4#, Zhi-Xian Yan4#, Tien-Yu Ko4#, Wei-Chen Peng4, Dun-Jie Jhan5, Yu-Hsiang Chang4, Jiun-Wei Fong4, Ming-Han Lu4, Wei-Chun Yang4, Jiann-Yeu Chen6, Ming-Yen Lu5, Baoquan Sun1,2*, Heng-Jui Liu4*, Ruiyuan Liu1,2*, Ying-Chih Lai4,6,7* |
单位： | 1State Key laboratory of Bioinspired interfacial Materials Science, institute of Functional nano & Soft Materials (FUNSOM), Soochow University, Suzhou215006, P. R. china. 2Jiangsu Key laboratory of Advanced negative carbon technol-ogies, Soochow University, Suzhou 215123, P. R. china. 3Department of Materials Science and engineering, national University of Singapore, Singapore 117574, Singapore. 4department of Materials Science and engineering, national Chung hsing University, taichung city 402202, taiwan. 5department of Materials Science and engineering, national tsinghua University, hsinchu 300, taiwan. 6innovation and development center of Sustainable Agriculture, i-center for Advanced Science and technology,national chung hsing University, taichung city 402202, taiwan. 7department of Physics, national chung hsing University, taichung city 402202, taiwan. |
摘要： | Integrating generative Artificial Intelligence (AI) chatbots with acoustic perception textiles allows everyday cloth-ing to retrieve information, seek advice, and perform tasks through voice interactions. Here, we present a deeplearning (DL)–empowered triboelectric AI acoustic textile (A-Textile) leveraging electrostatic charges on clothingfor imperceptible, active voice perception and AI access. The multilayered A-Textile features a composite coatingof three-dimensional SnS 2 nanoflowers (NFs) embedded in silicone rubber to enhance charge capture and trans-fer, along with a SnS2 NFs–decorated graphite-like carbonized textile for charge accumulation and preservation.This design maximizes the charge density on the textile, achieving a 21-volt output, 1.2 volts per pascal sensitivity,1- hertz resolution, and a wide sound response frequency range of 80 to 900 hertz. Using a well-trained DL model,the A-Textile precisely classifies and visualizes voice commands for internet-of- things control and cloud informa-tion access. Furthermore, we demonstrate its integration with ChatGPT, providing an intuitive interface for engag-ing with generative AI services to perform sophisticated tasks. |
影响因子： | 12.5 |
分区情况： | 一区 |
链接： |
责任编辑：郭佳