인피니언 8월20일부터
This page was machine-translated and may differ from the original. View original

Infineon and XMOS Provide Far-Field Voice Detection Using Audio Beamforming

Google 우선 소스Published2017.03.14 15:30
Combining Radar and Microphone Sensors with Audio Processor
Voice Source Identification and Distinction from Inanimate Object Noise


Infineon Technologies has partnered with XMOS to provide new building blocks for voice recognition.

By combining Infineon's radar and silicon microphone sensors with XMOS's audio processor, the solution delivers far-field voice capture using audio beamforming and radar target detection capabilities.



This maximizes sound recognition for various types of voice-controlled devices and ensures seamless execution of digital voice assistance. Suitable applications include smart homes, smart TVs and set-top boxes, secure keyless entry systems, and other voice-controlled consumer devices.

Currently, MEMS microphone performance limits system effectiveness. When multiple people speak, the system cannot accurately identify the location of the voice source and cannot distinguish noise from inanimate objects. These issues can be overcome by using Infineon's 60GHz 2Tx/4Rx radar IC (including antenna) and 70dB SNR microphone.

XMOS's audio processor analyzes signal data from Infineon's digital microphone array, adjusts angle and distance data from each microphone, and generates a beam toward the angle identified from the radar data.
To request a correction, reply or follow-up report on this article, see how to file a request. Previously published statements are collected in corrections & replies.
김지혜 Reporter