LONDON – Audience Inc. has announced the latest addition to its family of voice processor chips, the A1028.
The A1028 features technology that replicates the functions of human hearing to enhance sound quality and suppress noise thereby improving mobile speech recognition performance in noisy environments. The voice processor also extends Audience's noise suppression to support the speakerphone mode in mobile devices.
Audience (Mountain View, Calif.) is a privately held company founded in 2000. It's EarSmart technology mimics in a DSP chain the workings of the human inner ear and distinguishes and interprets sounds as people do, to enhance the primary voice signal and filter out unwanted background noise.
The A1028 system-on-chip processor improves on previous offerings from Audience mainly by enhancements targeting handheld speakerphone mode and automatic speech recognition (ASR) applications. The company did not provide more detail nor did it state what manufacturing process technology the A1028 is being implemented in.
The chip has customizable voice quality tuning capabilities, a post-equalization filter for voice color tuning and to allow handset manufacturers to manage frequency response, and a multi-band compander to improve audio quality and reduce distortion for end-users when receiving communication, or using the phone's speakerphone function.
To support design-in of the A1028 Audience has created a graphical design tool called AuViD 1.0. AuViD 1.0 provides visually-guided tools allowing handset manufacturers to easily tune and customize the audio features of their handset models. The A1028 chip is provided in a highly compact 2.7mm x 3.5mm, 40-pin WLCSP (0.5-mm pitch) package that can fit any handset style or design to support all existing mobile phone architectures.
"Several of the leading smartphones and advanced feature phones launched this year have placed an increasing importance on enhancing voice quality and supporting voice-enabled technologies," said Linley Gwennap, principal analyst of The Linley Group. "The voice processing capability offered by Audience is helping to drive this trend."
Handsets offering Audience's A1028 voice processor will be launching in the first half of 2011, the company said.
This is good product Audiance has come up with.
Sound engineering has got evolved a lot and there are very exceptional algorithms that enhance the audio quite well, but most of them are cpu power hungry, so it becomes difficult to implement on microprocessors as it required many DSP functionalities. This processor from Audiance will start some new practice in mobile and cordless handsets and will surely improve the quality of communication.
Voice processing capabilities will be an important feature for all the smartphones and tablets. Even though I've already seen few voice based applications in the past with the mobiles, but they wern't really accurate enough to recognise the right command. Voice to text convertors could also prove really useful.
Join our online Radio Show on Friday 11th July starting at 2:00pm Eastern, when EETimes editor of all things fun and interesting, Max Maxfield, and embedded systems expert, Jack Ganssle, will debate as to just what is, and is not, and embedded system.