Cadence Tensilica HiFi 5 DSP for audio/voice is the first IP core for high-performance far-field processing/AI-based speech recognition processing.

The integration of Rubidium’s feature rich technology into the CoolFlux DSP provides NXP licensees with access to hands free voice trigger and later also speech recognition capability with beam ...

That datasheet’s SoC diagram shows an audio DSP, too. We haven’t heard anything about speech recognition related to the Atom’s Smart Sound implementation.

Tensilica®, Inc. today introduced the HiFi Mini DSP core, the smallest, lowest power DSP IP core supporting always listening voice trigger and speech command modes. Optimized specifically for the ...

Cadence has introduced DSP intellectual aimed at neural network-based complex speech recognition on the local PCB, without the need for cloud-based services to do the heavy lifting.