Always-on smart microphone processor supports IoT applications
Cadence Design Systems has announced that Fortemedia has licensed the Cadence Tensilica Fusion F1 DSP as the engine of its next-gen smart microphone processor to support always-on voice trigger and sensor fusion capabilities for voice wake-up in mobile, Internet of Things (IoT) and consumer applications.
By configuring the Fusion F1 DSP to efficiently support voice processing and context-aware sensor fusion, Fortemedia’s latest solution will enable features such as automatic screen shutoff and ringer volume boost while devices are carried in pockets or purses, automatic reading of messages upon entering a car and low power voice triggering.
“The integration of Tensilica’s Fusion F1 DSP into our latest generation SAM101 DSP enables us to offer an extremely low-power solution with improved sensor fusion and voice triggering functions for always-on applications in the consumer market,” said Joseph Chen, Vice President, advanced hardware architecture at Fortemedia. “Cadence’s broad software partner ecosystem supporting the Tensilica Fusion F1 DSP provides our customers with an easy way to add additional capabilities.”
“The Fusion F1 DSP enables even lower energy for the always-on features in mobile and other consumer devices and will extend Fortemedia’s advantage over microcontroller based designs,” said Larry Przywara, Group Director of audio/voice DSP marketing at Cadence. “With the integration of the Tensilica Fusion F1 DSP in their latest smart microphone processor, Fortemedia can now deliver a leading-edge solution to enhance user experiences and speech communication.”
The Tensilica Fusion F1 DSP offers low energy, high performance control and signal processing for a broad segment of IoT/wearable markets. This highly configurable architecture is specifically designed to excel at always-on processing - including wake-on-voice and sensor fusion applications - that require a merged controller plus DSP, low energy and a small footprint. It can be designed into SoCs for wearable activity monitoring, indoor navigation, context-aware sensor fusion, face trigger, voice trigger and voice recognition.