http://www.embedded-computing.com/news/db/?10289 Does anybody know of this chip - sounds too good to be true. We'll all be out of a job! Hardy MOBILE WORLD CONGRESS - BARCELONA, Spain - February 11, 2008 - Audience today announced the industrys first voice processor based on the intelligence of the human hearing system and began sampling these new chips to mobile handset manufacturers. The Audience Voice Processor is the first custom IC that is modeled after the most efficient and accurate auditory system, the human hearing system. By thoroughly understanding the entire audio pathway - from the cochlea to the brainstem to the thalamus and cortex - Audience is the first company to deliver a commercial product based on the science of Auditory Scene Analysis (ASA), or the grouping and processing of complex mixtures of sound. Because the Audience Voice Processor handles signals the way people actually perceive specific sounds, it is able to identify and suppress noise sources in an extremely efficient and accurate manner. Audience will be displaying its new voice processor at Mobile World Congress in booth 7D50 as well as in the Innovation Marketplace. Both Audience booth locations are in Hall 7. "The Audience Voice Processor defines a new standard for robust, noise suppression, enabling unprecedented voice quality and more usability of rich voice and data applications," said Peter Santos, CEO of Audience. "People talking on mobile handsets will be able to hear and be heard everywhere from their cell phones, even in the noisiest places." Audiences Voice Processor receives a complex mixture of sound at overlapping frequencies, and organizes it into individual sources, in the same way people actually hear sounds. Regardless of whether the noise is local to the caller or remote over the mobile network, the processor uses several grouping cues to group all sound sources instantaneously, suppressing the noise and delivering the voice of interest clearly. "As the mobile phone market continues to grow, consumers are demanding clearer voice reception from their handsets," said Flint Pulskamp, wireless and mobile semiconductor analyst at IDC. "Improvements in non- stationary noise suppression, such as that offered by the new Audience Voice Processor, can make a dramatic difference in cell phone communications, offering handset users improved voice quality in noisy environments." Audience A1010 Voice Processor The Audience A1010 Voice Processor provides the most powerful and robust noise suppression technology available today. Whether the noise source is in the callers environment, or coming in over the cellular networks from the other end of the call, the Voice Processor instantaneously reduces multiple noise sources, such as airport PA systems, restaurant noise, car noise and street noise. The result is clear voice communications over mobile networks or VoIP applications, such as PC telephony and video conferencing, in places before unimagined. Audiences Voice Processor is a compact single chip that integrates audio acceleration logic, a powerful custom digital signal processor, audio peripherals and control interfaces. Its low power and small package design is optimized for mobile phones and portable wireless peripherals. The A1010 is packaged in a 2.7 x 3.5mm WLCSP that meets RoHS requirements. The Audience Voice Processor provides a complete voice quality enhancement solution that allows fast time-to-market and easy integration for handset manufacturers, OEMs, ODMs, and peripheral vendors. The processor is compatible with all handset types and cellular technologies. Audiences new Voice Processor sets the benchmark in five critical elements of an advanced noise suppression solution. - Instantaneous Noise Suppression - Enables Clear Communication Everywhere o Suppresses stationary and non-stationary noise up to 25 dB in < 500 milliseconds o Acoustic echo cancellation enables full duplex calls - Vivid Voice - Delivers Clear Speech in Noisy Environments o Increases Mean Opinion Score by 0.5 points in noisy environments o Easier to be understood by IVR systems in noisy environments - Efficient Design - Works Well with Limited Space and Power Budgets o Compact (2.7 mm x 3.5 mm WLCSP) and low-pin count package fits into even the smallest handsets o Adaptive power consumption maximizes battery power by shutting down the Voice Processor when not in use or needed - Ease of Integration - Designs-in Easily to All Mobile Handsets o Interoperates with all audio codecs and baseband platform architectures o Flexible dual Microphone system supports flexible configurations and handset types - more - - Extensible Architecture - Enables Differentiated Voice Services o Readily supports new voice services with software downloads o Voice Equalizer, Voice Stretch, ... o Supports all consumer mobile handset usage modes: close-talk (handheld), far-talk (speakerphone), and video telephony ITU Standard for Non-Stationary Noise Suppression Audience worked closely with several leading mobile carriers and mobile handset vendors to ratify a new standard for subjective testing of non-stationary noise suppressors, and in October 2007, the ITU-T standardization committee approved Amendment 1 Appendix III of the P. 835 standard. While the original P.835 standard recommended a test methodology for stationary noise testing, the new amendment enhances the standard by adding comprehensive test methodology for non- stationary noise. The amendment recommends test conditions for emulating real world conditions of multiple, moving non-stationary noise sources. This amendment is a major step in helping the mobile industry demand and ensures higher voice quality in real world environments. Mobile carriers, handset suppliers, and component vendors will all benefit from a common way of testing and measuring performance in these noisy conditions. Pricing and Availability Designed and priced to fit into mid- and high-tier phones, the Audience Voice Processor is sampling now. Sample pricing ranges from $5 - $7. The processor can be purchased through Audience directly, or through the companys international representatives and distributors. Volume pricing will vary with quantity and selection of voice features. Handset manufacturers will announce products with the Audience Voice Processor shipping in the first half of 2008. About Audience Audience is a voice processor company that enables clear communications anywhere with noise suppression technology based on the intelligence of the human hearing system. The technology is applicable across a broad range of consumer products where voice needs to be intelligible in noisy environments, and its first commercial product is for the mobile handset market. Audience was selected as one of two finalists in the category of Most Innovative True Mobile Start-Up for the "2008 GSMA Mobile Innovation Global Awards." The company is one of 34 founding member companies of the Open Handset Alliance and the only one with advanced noise suppression technology. Investors in Audience include Vulcan Capital, NEA, Tallwood Venture Capital and VentureTech Alliance. Audience, www.audience.com, is based in Mountain View, California.
Breakthrough in noise reduction?
Started by ●March 17, 2008
Reply by ●March 17, 20082008-03-17
HardySpicer wrote:> Does anybody know of this chip - sounds too good to be true. We'll all > be out of a job!But does it make Julienne fries? Quite a list of superlatives in that press release. What's the old saying, "If it sounds too good to be true, it probably is."? I just completed a voice processing project myself, from which I concluded that our understanding of the hearing process is really only rudimentary. They claim "[thorough] understanding [of] the entire audio pathway - from the cochlea to the brainstem to the thalamus and cortex". I'll reserve judgment until more specific information is available. Greg
Reply by ●March 17, 20082008-03-17
HardySpicer wrote: (snip)> The Audience Voice Processor is the first custom IC that is modeled > after the most efficient and accurate auditory system, the human > hearing system. By thoroughly understanding the entire audio pathway - > from the cochlea to the brainstem to the thalamus and cortex - > Audience is the first company to deliver a commercial product based on > the science of Auditory Scene Analysis (ASA), or the grouping and > processing of complex mixtures of sound. Because the Audience Voice > Processor handles signals the way people actually perceive specific > sounds, it is able to identify and suppress noise sources in an > extremely efficient and accurate manner.It would be nice for the readers of the newsgroup to explain a little about what you did that hasn't been done before. That is, some technical details. Hopefully there are some that aren't secret. Any patents yet? -- glen
Reply by ●March 18, 20082008-03-18
Hi: .... "> The Audience Voice Processor is the first custom IC that is modeled> after the most efficient and accurate auditory system, the human > hearing system. By thoroughly understanding the entire audio pathway - > from the cochlea to the brainstem to the thalamus and cortex - > Audience is the first company to deliver a commercial product based on > the science of Auditory Scene Analysis (ASA), or the grouping and > processing of complex mixtures of sound. Because the Audience Voice > Processor handles signals the way people actually perceive specific > sounds, it is able to identify and suppress noise sources in an > extremely efficient and accurate manner...."Sounds like a long winded way of saying they've subbanded the sound into a Bark Scale, then faffed around with it! Look => http://ccrma.stanford.edu/~jos/bbt/Bark_Frequency_Scale.html