CEVA and Retune DSP announced that the Retune VoiceSpot Wake Word Engine is now optimized and available for CEVA’s audio/voice DSPs. This includes the CEVA-BX, CEVA-X, and CEVA-TeakLite families.

VoiceSpot is a wake word and small vocabulary ASR engine, which allows for voice-wake and command and control on memory-constrained, battery-operated edge devices.

It boasts high performance levels in a 30 to 35KB typical model size and a total memory footprint of under 80KB.

The audio/voice DSPs from CEVA are deployed in battery-operated edge devices for voice activation and control. The DSPs are fitting for hosting wake word engines at low-power standby. Further, they’re also able to run complex front-end algorithms to improve voice intelligibility.

Per a company press release, CEVA's scalable audio and sensor hub DSPs are optimized for sound processing applications ranging from always-on voice control up to multiple sensors fusion. They have been specifically designed to tackle multi-microphone speech processing use-cases, high quality audio playback and post-processing, and on-device sound neural network implementations.

For more information, visit https://www.ceva-dsp.com/app/audio-voice-and-speech/.