Audience on Monday unveiled a new lineup of next-generation advanced voice processors for mobile devices due out this year, which build on the chip maker's human hearing system-based audio processing technology.
The upcoming Audience eS700 series of processors should start appearing in smartphones by the second half of 2014, Audience said. The next-generation audio processing platform adds Audience's new VoiceQ to its suite of features, a technology that allows a "device to continuously listen to its surroundings, and act upon a configurable voice command without the need for interaction via touch, with minimal battery life impact," according to the company.
Armed with an Audience eS700 series voice processor and always-on VoiceQ codecs, smartphones and mobile devices will enable users to wake up their phones and issue an instruction like "Okay, Audience — play music" with no pause between those two commands.
"We believe that dependable, always-on voice detection and actuation is the next must-have mobile technology," Peter Santos, president and CEO of Audience, said in a statement. "Our experience in delivering low-power, high-performance Advanced Voice makes us uniquely capable to deliver on the promise of a compelling always-on voice experience."
Though VoiceQ keeps the audio processor in an always-on state, it's an ultra-low power draw at less than 1.5 mA of battery current drain, according to the chip maker.
Audience made a name for itself several years ago with its earSmart noise-suppression technology utilised by top handset makers like HTC and Samsung. The company's approach to providing clearer audio has been to crunch the data supplied by multiple microphones to emulate the way our own organic ears work rather than using "beam-forming" techniques for signal processing like many of its competitors.
The upshot is that Audience claims its audio processors and codecs are better suited to provide consistent, quality voice representation regardless of how a device is held or tilted by users. The benefits play out whether a person is holding a phone at an odd angle or when a device is set on speakerphone and being listened to by multiple parties.
The upcoming Audience eS700 line of standalone voice processors and accompanying eS750 range of smart audio codecs add a number of new features to the company's currently available lineup of earSmart solutions.
In addition to the always-on VoiceQ feature, the eS700 line includes products that provide "industry-leading" signal-to-noise ratio performance for stereo headphones and earpieces, Audience's fourth-generation Advanced Voice technology, and noise-suppression support for up to three microphones capable of dealing with windy conditions.
Audience is also touting its latest advances in speech-restoration technology for improving voice quality "in even the harshest noise environments," its full-band (48 kHz) voice processing, and better accuracy achieved with its third-generation Assisted Speech Recognition technology.
With the release of the eS700, Audience is also making available a new API for mobile device OEMS "to access these features, and create apps that deliver new user experiences and new levels of touch-less interaction with mobile devices," the company said.
The first products in the new series are the eS704 and eS702 Advanced Voice processors, the eS754 processor and codec combo with VoiceQ included, and the eS752 platform without VoiceQ. All of the new products are currently sampling to Audience customers, the company said.
Image: Flickr (seizethedave)