03 Jan 2013

Tensilica Introduces Low Power DSP IP Core

Tensilica has introduced the HiFi Mini DSP (digital signal processor) core, that supports always listening voice trigger and speech command modes.

Optimized specifically for the smallest area and lowest power in smartphones, tablets, appliances, and automotive applications, the HiFi Mini DSP IP core enables a hands-free experience.

Tensilica is working with Sensory and other software partners that will provide the voice-activation, speech command recognition, voice pre-processing and noise reduction products optimized on the HiFi Mini DSP.

“Voice activation and speech command are essential ingredients in making devices much more user friendly, and we see that the market for devices utilizing this technology will explode in the years ahead,” stated Michael Morgan, mobile devices senior analyst with ABI Research. “A number of companies are working on the software side, but it’s also important to have a very low power DSP to run that software so battery life is not meaningfully impacted. Tensilica’s HiFi Mini will help drive this market.”

Tensilica optimized the HiFi Mini DSP core to be as small and power efficient as possible for voice trigger and voice recognition in two major ways. First, the core uses compact 40-bit encoding, which significantly improves code size. Second, Tensilica added efficient16-bit instructions that are optimized for voice and audio codecs. The result is a post-route core that’s only 0.039 mm2 in 28 nm HPL.

“Power is the single most important factor in enabling always-on listening capability in mobile devices. Using Sensory’s Truly Handsfree™ voice control technology, HiFi Mini is able to achieve less than 88 uW of power for the core in 28 nm HPL, achieving both the lowest power consumption and uncompromising accuracy for speech recognition,” stated Larry Przywara, Tensilica’s senior director of mobile multimedia. “The combination of ultra-low power and small area makes HiFi Mini an attractive addition to mobile as well as other consumer electronics. And as voice control emerges as the natural interface, we expect it will become more ubiquitous as it migrates to automotive, consumer appliances and potentially industrial control.”

Most popular news in Processing & embedded

Type 6 starter kits for modules with Intel 6th gen. core processors
Multi-core RTOS brings robustness & performance to SoCs
PowerVR GPU provides advanced graphics in automotive SoC
Molex & Cisco join MSA to develop double-density QSFP interfaces
Stackable FPGAs with interfaces that are “OneBank” compatible

All news in this channel | All news


Share this page


Want more like this? Register for our newsletter








De-bugging embedded systems Dr Johan Kraft | Percepio
Embedded systems debugging - overcoming inadvertent obstacles
Debugging embedded systems running a Real-Time Operating System (RTOS) is made simpler by the use of software tracing, which allows software events to be traced in order to monitor and better understand the code’s execution. This can be useful during debugging and optimisation.
Training
Online - Effective Vector Network Analyzer Measurements
How to make effective VNA measurements at RF and microwave frequencies

More training courses

Whitepapers
R&S 4G LTE Whitepaper
Read this authoritative and comprehensive whitepaper on the 4G LTE-Advanced features and capabilities in this whitepaper from Rohde & Schwarz.

More whitepapers










Radio-Electronics.com is operated and owned by Adrio Communications Ltd and edited by Ian Poole. All information is © Adrio Communications Ltd and may not be copied except for individual personal use. This includes copying material in whatever form into website pages. While every effort is made to ensure the accuracy of the information on Radio-Electronics.com, no liability is accepted for any consequences of using it. This site uses cookies. By using this site, these terms including the use of cookies are accepted. More explanation can be found in our Privacy Policy