矢量语音传感器微阵列

Vector Speech of Sensor Micro Array

人工智能的普及促进了语音交互技术的发展,语音传感器阵列作为智能语音交互的硬件前端,成为语音交互领域的前沿研究方向。矢量语音传声器自有的偶极子指向性、零点深度以及阵列体积小便于集成的特点特别符合语音交互技术对硬件设备的要求。基于此,通过采用两组矢量敏感单元"共点正交"形成矢量微阵列实现声源空间锐化波束指向,其不受瑞利限与空间采样率限制,与传统空间离散分布的声压麦克风阵列有着本质区别,是矢量微阵列的核心优势所在。矢量微阵列传声器弥补了现有双麦阵列的不足,具有更为广阔的应用前景,作为智能语音交互的硬件前端,对推动智能语音交互领域的发展具有重要意义。

The popularization of artificial intelligence promotes the development of voice interaction,speech sensor array is the hardware front end of intelligent speech interaction,it has also become a cutting-edge research direction in the field of voice interaction.Vector voice microphone has its own characteristics of dipole directivity,zero depth and array volume,which is easy to integrate,especially in line with the requirements of voice interaction technology for hardware equipment.In this paper,two groups of vector sensitive units are used to form a vector microarray to realize the spatial sharpening beam pointing of sound source,it is not limited by Rayleigh limit and spatial sampling rate,it is essentially different from the traditional spatially discrete sound pressure microphone array,which is the core advantage of vector microarray.Vector micro array microphone makes up for the deficiency of the existing dual microphone array,it has a broader application prospect.As the hardware front end of intelligent voice,it is of great significance to further promote the development of intelligent voice interaction.