Next-generation voice interfaces for smart things

XMOS has launched the XVF3610 and XVF3615 voice processors: next-generation high-performance two-mic voice interfaces for wireless speakers, TVs, set-top boxes, gateway products, smart home appliances and more.

Constructed on its xcore.ai chip infrastructure, the devices provide industry-leading voice processing solutions in an easy-to-integrate and cost-effective package. The designs indicate an evolution of the XVF3510 voice processor currently used within Amazon Alexa systems and offer powerful audio echo cancellation and interference cancellation algorithms to suppress noise from dominant sources and allow cross-room barge-in. The device also incorporates automatic audio reference delay calibration – a critical capability for voice-enabled TV systems - expanding the range of devices and environments where voice interfaces can be implemented.

The XVF3615 adds embedded Amazon wakeword for single-pass Alexa enabled systems, allowing manufacturers to offload wakeword processing from their host SoC systems. In the face of a challenging supply chain, XMOS can confirm that the processors are available in volume on standard lead times.

In an further development in the range of voice solutions offered, the company has launched an alpha phase for targeted customers for the all-new ‘Avona’ voice reference design. Employing the flexibility of the xcore.ai platform, Avona offers a customisable reference design for voice, wakeword, speech-to-intent and intelligent voice applications.

Aimed at intelligent IoT applications, this voice reference design enables engineers to include a keyword, event detection or advanced local dictionary support to produce a complete voice interface solution. Partners and customers may also produce their own voice-based solutions utilising the core SDK. Programmed In C or C++ and including a FreeRTOS environment for user application code, the score SDK supports bare-metal and RTOS use, proviing customers complete flexibility and the capability to add bespoke differentiation for the final product.

Mark Lippett, CEO, XMOS, said: “The IoT market is creating new verticals and opportunities at breakneck speed, and we are seeing significant demand within the smart home. As more applications become commercially attractive or viable, engineers and designers need to rely on hardware that offers agility and cost-effective performance without compromising on quality. Our new range of voice solutions delivers another weapon in their arsenal when it comes to voice control, enabling designers to continue to push the boundaries of voice innovation in the smart home and beyond.”

Rob Fisher, product director, XMOS, said: “Versatility is the key with all three of these new voice solutions, inherent in the structure of the xcore.ai chip. Designers are empowered to make choices: what balance of compute do we want? How much of the voice element is customisable? Are we coding on bare metal or in FreeRTOS? That dexterity will help them innovate in ways that they otherwise couldn’t.”