Knowles Audience™ eS800 series

The new eS800 products boast the highest performance and richest advanced voice feature set for advanced voice, with new technologies designed to support consumer devices beyond smartphones.

The eS800 series is made up of the eS804 stand-alone advanced voice processor and The World's Most Intelligent Voice Processor Algorithm.

New and Improved advanced voice technologies in the eS800 series include:



Amazon Echo

Noise suppression with support for far field

Traditional voice communication and speech recognition fail at distances greater than an arm’s length. Knowles far field technology allows advanced voice capabilities, including “barge-in” technology, voice wake, Automatic Speech Recognition (ASR) assist and noise suppression, to operate at distances of more than five meters. 




Audio barge in

Audio “Barge-in”

Software's new “barge-in” feature enables a device to hear and act upon a spoken voice command, even if audio is already playing. This means users can be listening to music or watching video and give a command without interrupting the entertainment experience. “Barge-in” is designed to work with leading speech recognition engines.



Voice compass

Voice compass

The second generation of audio focus includes a new voice compass feature for identifying, within the user interface, up to 16 different locations of the audio source. Voice compass then suppresses background noise, enabling the recording of meetings or conversations in noisy environments. Voice compass also enables the ability to tag talkers and selectively listen to them.



gray blazer

5th generation advanced voice

The latest generation of software includes improved accuracy for user trained keywords resulting in less false wake-ups. The eS800 series also features several voice quality improvements for handset usage including: new noise suppression algorithms based on machine learning techniques, SNRI improvements of more than 6dB enabling clear calls in challenging environments, and improved positional robustness for natural and smoother sounding voice quality when holding the device in almost any position.