Advertisement

XMOS unveils two voice processors and reference design

XMOS has launched two voice processors for smart devices and announced its alpha program for the new Avona voice reference design.

XMOS has launched its XVF3610 and XVF3615 voice processors, which are two-mic voice interfaces for devices such as wireless speakers, TVs, set-top boxes, smart home appliances, and gateway products. The XVF3615 is an Amazon wake word-enabled variant of the new platform. The company also announced its alpha program for the Avona voice reference design.

Building on the SVF3510 voice processor already used in the Amazon Alexa systems, the XVF3610 and XVF3615 voice processors, based on the XMOS xcore.ai chip infrastructure, offer audio echo cancellation (AEC) and interference cancellation algorithms to suppress noise from dominant sources and enable cross-room barge-in. They also include automatic audio reference delay calibration, which is a critical capability for voice enabled TV systems, expanding the range of devices and environments where voice interfaces can be implemented, said XMOS.

Dev kits for the XMOS XVF3610 voice processors

XMOS XVF3610 voice processor development kit. Click for a larger image. (Source: XMOS)

In addition, the XVF3615 offers embedded Amazon wake word for single-pass Alexa-enabled systems, allowing manufacturers to offload wake-word processing from their host SoC systems.

The XVF3610, housed in a 60-pin,  7 × 7-mm QFN package, is available now in distribution, and will be followed by the SVF3615 in January 2022. (Click here for a demo of the XVF3615.) Both devices will be available in volume with standard lead times. Dev kits are available.

XMOS also rolled out its Avona voice reference design for intelligent IoT to targeted customers. Also leveraging the xcore.ai platform, Avona provides a customizable reference design for voice, wake word, speech-to-intent, and intelligent voice applications. The voice reference design allows engineers to incorporate keyword, event detection or advanced local dictionary support to create a complete voice interface solution.

Partners and customers can also develop their own voice-based solutions using the xcore software development kit (SDK), which supports both bare-metal and RTOS use. The reference design will be available in early 2022 for the general industry.

Advertisement



Learn more about XMOS

Leave a Reply