Infineon says the solution provides optimal sound recognition and flawless execution for digital voice assistance across a broad range of voice-controlled devices. Target applications are especially smart home/voice assistants as well as smart TV and set top box, secure keyless entry systems, and other voice-operated consumer devices.
The 70dB SNR microphones are based on the dual backplate MEMS technology from Infineon and are well suited for far field voice capturing and beamforming. In addition, improving the SNR of the microphone further enhances the performance.
The XMOS audio processor processes the signal data from an array of Infineon PDM microphones, adjusting the angular and distance data from each microphone to produce a beam at an angle identified by the radar data. A lit LED indicates presence detection and where sound is taken from.
The combination of Infineon radar and XMOS beamformer allows the microphone to target a specific target source precisely, even as the target moves around a room of people talking and inanimate sounds. The microphone delivers a superior user experience to existing voice-controlled systems, with clear understanding of commands and flawless execution that prevents unwanted activations of devices. By shifting the time base of each microphone while suppressing individual mic differences, the microphones are focused on a specific target to optimize sound recognition.
The performance of current MEMS microphone limits the effectiveness of systems: when multiple persons are speaking, the veracity and location of the voice source cannot be precisely identified and separated from inanimate object noise. Infineon’s 60 GHz 2Tx/4Rx radar IC with accompanying antenna and the 70dB SNR microphone helps to overcome these impediments. The microphones are based on the dual backplate MEMS technology from Infineon and are well suited for far field voice capturing and beamforming.
www.infineon.com/audiobeamforming | www.xmos.com