Development kit offers superior Alexa Voice Service

With the Cirrus Logic IC and software design, the Voice Capture Development Kit for Amazon AVS helps manufacturers quickly get to market with new Alexa-enabled products that feature high-accuracy wake-word triggering and command interpretation even in noisy environments and during music playback.

The low power Voice Capture Development Kit for Amazon AVS includes a reference board that features Cirrus Logic’s CS47L24 smart codec, CS7250B digital MEMS microphones and SoundClear algorithms for voice control, noise suppression and echo cancelation.

The turnkey voice capture reference design enhances “Alexa” wake word detection and audio capture in real world conditions, even from moderate distances in noisy environments, and enables users to reliably interrupt loud music or Alexa response playback. The smart codec uses an on-chip, high-performance digital-to-analog converter (DAC) with a two-watt mono speaker driver to enable high-fidelity audio playback.

“We’re excited to be working with Cirrus Logic to help OEMs bring Alexa to more smart speakers and other audio form factors,” said Priya Abani, director, Alexa Voice Service. “Cirrus Logic’s Voice Capture Development Kit for Amazon AVS delivers advanced acoustic tuning along with proven hardware and software components to allow device-makers to bring products to market faster and more efficiently.”

“With our expertise in audio and voice ICs and software, we are giving manufacturers of smart home applications a powerful, easy-to-use voice capture development kit for creating Alexa-enabled products,” said Carl Alberty, vice president of Marketing, Cirrus Logic audio products.

“Our AVS development kit delivers superior voice command performance that when combined with the Cirrus Logic tools and software provided, enables OEMs to bring high-fidelity speakers with superior Alexa voice interaction to market faster.”

Cirrus Logic’s voice capture solution elevates the user experience by suppressing noise and other real world interference for more accurate and reliable voice interactions. This technology improves “Alexa” wake word detection in both quiet and noisy environments and with the user several meters away from the device.

Cirrus Logic’s echo cancelation technology is critical to achieving a superior user experience by allowing the user to “barge” into or interrupt loud music playback and Alexa responses, so Alexa can respond accurately to new requests.

The ultra low noise floor and wide dynamic range (130 dB) of Cirrus Logic’s MEMS microphones assure precise voice capture in challenging noise conditions, enabling Cirrus Logic’s SoundClear algorithms to block noise that would otherwise interfere with Alexa wake word and request accuracy.

Cirrus Logic’s smart codec integrates hi-fi DACs, a stereo headphone amp and mono speaker amp to provide OEMs with a low cost bill of materials for products ranging from high-end speakers to simple digital assistants. Designed with the needs of ultra low power portable devices and accessories in mind, it typically consumes 80% less power versus competing solutions.

The kit is a complete solution that includes a voice capture board with high performance two-microphone array, Raspberry Pi 3 (RPi3), speaker and a microSD card preloaded with all required firmware for instant productivity.

Cirrus Logic’s control console simplifies operation of the various RPi3 applications and provides a robust, user-friendly interface to perform acoustic tuning and diagnostic functions. The voice capture reference board’s schematic design and bill of material are designed for use in most AVS applications with minimal customisation, further reducing time-to-market.