Graphene-based dual-function acoustic transducers for machine learning-assisted human-robot interfaces

Human-robot interface (HRI) electronics are critical for realizing robotic intelligence. Here, we report graphene-based dual-function acoustic transducers for machine learning-assisted human-robot interfaces (GHRI). The GHRI functions both an artificial ear through the triboelectric acoustic sensing mechanism and an artificial mouth through the thermoacoustic sound emission mechanism. The success of the integrated device is also attributed to the multifunctional laser-induced graphene, as either triboelectric materials, electrodes, or thermoacoustic sources. By systematically optimizing the structure parameters, the GHRI achieves high sensitivity (4500 mV Pa-1) and operating durability (1 000 000 cycles and 60 days), capable of recognizing speech identities, emotions, content, and other information in the human speech. With the assistance of machine learning, 30 speech categories are trained by a convolutional neural network, and the accuracy reaches 99.66% and 96.63% in training datasets and test datasets. Furthermore, GHRI is used for artificial intelligence communication based on recognized speech features. Our work shows broad prospects for the development of robotic intelligence.

Automated summary

Graphene-based dual-function acoustic transducers have been developed for machine learning-assisted human-robot interfaces. The integrated device functions as both an artificial ear and an artificial mouth, utilizing triboelectric acoustic sensing and thermoacoustic sound emission mechanisms. With high sensitivity and durability, it can recognize various information in human speech. Machine learning techniques have been employed to achieve accurate speech recognition and facilitate artificial intelligence communication.