Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Processors/DSPs

Voice, gesture controls double as always-on observers

Posted: 02 Jun 2014 ?? ?Print Version ?Bookmark and Share

Keywords:always-on? voice? Dash? Siri? Glass?

Audio analytics are already used to detect specific classes of sound (breaking glass, gunshots), or simply for keyword detection to trigger video data retrieval.

Texas Instruments' latest ultra-low-power DSP, the TMS320C5517, is aimed at demanding applications such as audio and video, but also biometrics and other specific analytic applications. With a footprint of 10x10mm, the chip is designed to support face detection, object tracking and voice recognition in a broad range of portable applications.

Toshiba Electronics announced it will expand its line-up of image recognition processors with the TMPV7502XBG, an 11x11mm chip drawing only 0.6W and designed for small-size camera modules.


Figure 2: Toshiba's TMPV7502XBG is designed for automotive applications, form implementing Advanced Driver Assistance Systems (ADAS), specifically.

The IC is aimed at cars, for implementing ADAS. With cameras looking in all directions, ADAS not only increase road safety by recognising lanes, road signs, vehicles and pedestrians, they have the potential to convert every vehicle into yet another collateral data acquisition tool for whoever runs the service (think of Google's driverless car and your private conversations being listened to).

So by virtue of progress, it looks like always-on analytics (voice, gesture, biometric) will pair, more often than not, with always-on connectivity and augmented reality, beyond the NSA's wildest dreams. Under the promises of more conveniences or an easier life, every gesture, every spoken word may create actionable data, sometimes triggering overzealously configured software packages.

As a by-product of this constant situational awareness, will individuals reinforce the mute and inexpressive attitudes that have been developed through the intensive use of short text messaging, or will they gesticulate more and talk their way as if surrounded by a cloud of servants?

- Julien Happich
??EE Times Europe

?First Page?Previous Page 1???2

Article Comments - Voice, gesture controls double as al...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top