Even if you haven't heard of Audience, there's a very good chance you (or a close friend or family member) have used a product with one of its audio processing chips installed. The company, which prides itself in its noise-cancelling prowess, is taking to CES to launch its latest high-end processor, dubbed the eS515. This particular chip offers a new high-performance, low-power codec subsystem and integrates a handful of impressive features along with it. First on the laundry list of improvements is support for up to three mics on a singular device; while we've seen the three-mic setup on a limited scale in the past (Qualcomm has done it on its development phones), Audience's implementation may be the first to arrive on commercially available phones. Since it's currently sampling to manufacturers, we may not have to wait terribly long.
In addition to the three-mic support, the eS515 also throws in a few other handy tools, such as de-reverb, which is meant to significantly reduce the voice echo users normally experience on speakerphones and in large rooms; a selective audio capture feature called Audio Zoom, which lets you switch back and forth between a bi-directional recording mode and single-direction narrator mode; new hardware-accelerated speech recognition algorithms that's geared to interpret your voice more accurately; and dual-mic noise suppression when taking video. It all sounds pretty tempting, and we're eager to see how well Audience holds up on its claims -- we're still waiting to hear which upcoming devices will have the chip installed, but our guess is that it'll show up on a handful of premium smartphones in the coming year. We've got the press release below for your dissection.
Audience Introduces the earSmart eS515 – The World's First Smart
First in Family of Smart Sound Processors Combines New Audience Codec Technology with Proven Advanced Voice Processing For New Levels of Personal Presence on Mobile Devices
MOUNTAIN VIEW, Calif. – Jan. 07, 2013 – Audience®, Inc. (NASDAQ: ADNC), the leader in advanced voice and audio processing for mobile devices, today announced the world's first Smart Sound Processor, the earSmart eS515. The earSmart eS515 Smart Sound Processor combines the company's award-winning Advanced Voice processing technology with its first high-performance, low-power audio codec for a best in class voice, speech recognition and multimedia experience on a mobile device.
Consumer demand has shifted to more sophisticated mobile devices with greater processing power, slimmer designs, larger displays and advanced multimedia features. Mobile device manufacturers are looking to tightly integrated processing solutions that deliver more, for less power. The earSmart eS515 Smart Sound Processor responds to this need by delivering a number of industry first innovations: simultaneous 3-microphone processing, optimized Automatic Speech Recognition (ASR), Mobile Audio Zoom and Super Wideband support for Voice over IP (VoIP), combined with a robust audio codec designed specifically for the newest mobile devices.
"In recent months, Audience has demonstrated its commitment and passion for delivering the best-sounding voice and audio experience on pioneering mobile devices like the Samsung Galaxy Note II, the Google Nexus 10, the Motorola Razr I, and the world's thinnest Android smartphone, the BBK Vivo X1." said Peter Santos, president and CEO, Audience. "The earSmart eS515 Smart Sound Processor is the first silicon to offer Advanced Voice technology integrated with a complete audio codec subsystem – it takes us to the next stage in sound processing, providing our customers with a level of performance, integration, efficiency and auditory presence never before experienced."
Be Heard – With Best in Class Voice Processing
The earSmart eS515 features Audience's third generation Advanced Voice technologies. The earSmart eS515 delivers the world's first three-microphone technology where all three microphones can be used simultaneously to gather more environmental information around the user and deliver vastly improved voice quality. In addition, the earSmart eS515 supports high sample-rate VoIP calls, offering the industry's best voice quality for narrowband and wideband networks. The earSmart eS515 is also the first sound processor to offer de-reverberation for mobile devices – removing the echo effect in spaces such as conference rooms and hallways.
Be Understood – With Optimized ASR Assist
ASR Assist technology from Audience directly addresses the challenge faced by many speech recognition applications today, namely their failure to recognize spoken words and complete assigned tasks because of disruptive background noise. The earSmart eS515 uses custom hardware-accelerated algorithms to isolate voice from surrounding environmental noise, dramatically improving the user experience of speech-enabled applications such as virtual assistants and voice search. Mobile devices equipped with Audience ASR Assist technology deliver improved speech application reliability, accuracy and task completion – even in noisy, distracting environments.
Be There – With Enhanced Media Capture and Playback
Mobile devices today are relied upon for media capture as much as they are for communication. The desire for captured audio to have the same high-definition (HD) quality as video has never been more apparent. The earSmart eS515 Smart Sound Processor features the world's first two-microphone 48 KHz noise suppression implementation for the recording of clean, HD audio. The earSmart eS515 also features Audio Zoom, the world's first selective audio capture feature to be deployed for mobile devices. Audio Zoom allows users to dynamically switch between narrate mode, with a single speaker, to interview mode, where the person holding the device can "interview" another person. Interview mode leverages Audience's industry leading stationary noise reduction technology to capture both voices with crystal clear accuracy while still suppressing background noise.
Advanced Voice + Powerful Integrated Codec = Smart Sound Processor
The earSmart eS515 Smart Sound Processor is a high performance, audio processing solution with significant integration and flexibility. The solution includes an Audience Advanced Voice Processor core and a hardware accelerator engine, optimized to run computationally intensive audio algorithms with low power consumption. In addition, the earSmart eS515 processor includes a best in class stereo audio codec. Before the eS515, codecs this advanced were only available in discrete solutions. The Audience codec subsystem consists of analog to digital converters (ADCs) on the record path and digital to analog converters (DACs) on the playback path. The codec subsystem includes stereo class D speaker drivers, stereo class G headphone drivers, an earpiece driver, and two line outputs.
The earSmart eS515 is currently sampling to customers globally. For more information on the Audience earSmart family of products and more detailed specifications on the eS515, please go here.