AMD TrueAudio Enables Enhanced User/Speech Recognition And Commands

jww20

Weaksauce
Joined
Jan 9, 2003
Messages
72
true_audio_4.png

AMD Developer Summit on November 11-13 at Santa Clara, CA will have seminars on the TrueAudio technology and capabilities of the new R9-290X, 290 and R7-260X graphics cards.

From the Max PC interview:

Maximum PC: In one sentence TrueAudio is:

AMD: A programmable audio core built into the GPU, representing our effort to breathe life into game audio environments as the programmable graphics pipeline breathed life into the diversity of PC graphics.

MPC: I didn’t get to attend the briefing but if I get this; AMD has integrated Tensilica HiFi2 EP DSPs directly into the die or on the package or on the PCB? It says multiple but how many exactly?

AMD: The entire AMD TrueAudio hardware block is built directly into the die of the AMD Radeon R9 290X, R9 290 and R7 260X GPUs. While I cannot disclose the quantity, I can say that the game developers we’ve been speaking to have been overjoyed by the hardware capabilities we’re providing.

(AMD has since disclosed to us that it has three Tensilica DSPs on the die).

http://pixelrant.com/2013/10/08/everything-you-wanted-to-know-about-amds-new-trueaudio-technology/

From the AMD Next Generation User Experiences:

"Being able to gesture to the computer is just the start of the next generation of natural user interfaces. Nuance, an industry leader in speech recognition and the company behind the highly acclaimed Dragon Naturally Speaking products, will be showing how AMD’s TrueAudio technology can improve speech recognition in applications by applying complex post-processing that significantly improves audio playback quality, removes background noise and reduces the latency of analyzing speech input. AMD TrueAudio is just one example of AMD innovation that is enabling software developers to invent new ways for users to interact with their computers.

AMD has also been working on facial recognition technology that can allow users to login by simply looking at their computer. Facial recognition, much like gesture control, requires significant parallel processing power – and area where APUs really excel – and thanks to the A-Series APU’s Radeon GPU, the user’s face can be analyzed quickly to grant them access to their machine. Thanks to the work AMD, Nuance and CyberLink have been doing with audio technologies, face login will also be supplemented with voice authentication.

AMD and its partners will show off just what is possible with the power of the APU at the Innovative Client Experiences track during the AMD Developer Summit. Whether it is new ways to interact with your PC or running smartphone and tablet Android apps on a PC’s big screen, AMD and its partners are enabling new ways for users to enjoy their PC."

http://webcache.googleusercontent.com/search?q=cache:BqXknu6ePpQJ:developer.amd.com/community/blog/accelerated-processing-units-power-the-next-generation-of-user-experiences/+&cd=1&hl=en&ct=clnk&gl=us
 
Interesting article. Can't wait to see information from AMD's developer summit.
 
This will be amazing.

I was using voice recognition at one point to perform in-game commands. There was always a 2+ second delay for the software to process the command which meant it could not be used in alot of twitch scenarios. It did work very good though.

If AMD can speed this up to less than 500ms that would be amazing.
 
Back
Top