Speech Technology Magazine

 

Conexant Intros New Voice Input Processor for Smart TVs

LG is the first TV manufacturer to adopt Conexant's new Voice Input Processor with embedded speech recognition engine.
Posted Jan 8, 2014
Page1 of 1
Bookmark and Share

Conexant Systems yesterday at the Consumer Electronics Show in Las Vegas introduced the next generation of its high-performance far-field voice input processor system-on-chip (SoC) designed specifically for smart TVs, the CX2092x.

Conexant's new chip uses third-generation voice processing technology to deliver superior voice control with excellent speech recognition hit rates and voice communications with increased clarity in far-field conditions up to four meters away from the TV.

LG is the first to adopt the CX2092x and will implement it in its 2014 TV lineup.

"This marks the third consecutive year that tier-one TV manufacturers have turned to us for our innovative far-field voice processing technology," said Saleel Awsare, Conexant vice president and general manager, in a statement. "In the future, the concept of a smarter audio experience will apply to much more than TVs. Conexant's audio solutions with far-field technology will allow people to control everything from their tablets to home appliances using only their voice."

The new chip is part of Conexant's AudioSmart solutions. With a low-power, small-footprint speech recognition engine running within the chip, the CX2092x can always be listening for a wake-up voice command while the rest of the TV is powered off. The CX2092x executes this always-listening mode in an ultra low-power state, enabling TVs to meet worldwide energy standards for standby power.

According to LG, the ability to do this, combined with echo cancellation that allows users to talk to the TV while it is on from anywhere in the room, within four meters, sets the CX2092x apart from the competition.

Key features include the following:

  • Fully-integrated Wake-on-Voice solution with embedded third-party speech recognition engine;
  • Excellent speech recognition hit rate and clear voice quality;
  • Compatibility with multiple leading speech recognition vendors;
  • Reference design with pre-tuned hidden microphone module; and
  • Dual 24-bit ADC and microphone preamp with independent microphone bias supply.

Page1 of 1