Harvesting the richness of space

The dim solar light flickered as the cloud of dust rose from the surface of the asteroid.  Three suited figure stood gripping tethers to hold them down against the gentle spin.  Gravity was weak.  As the dust cleared one of the figures crouched next to the excavation.  A suited hand brushed aside the dust that had settled and revealed metallic crystals that glinted in the light.  Glints that meant riches beyond imagine.

A group of technology innovators and NASA experts have teamed up to found and fund a company, Planetary Resources, to explore and commercialise the resources available on asteroids and other non-Earth territories.  An announcement and update to the website is scheduled for tomorrow, 24 April.  Visit the website here: http://www.planetaryresources.com/ See the wiki page here: http://en.wikipedia.org/wiki/Planetary_Resources



The computer on the wall

Sporting a device reminiscent of the shoulder weapon from Predator, a man slowly appoaches a white-washed wall. Suddenly, at the touch of a finger, images and words spread out around his hand, giving him direct access to the previously unseen digital universe.  His gestures and manipulations change that world.  Then, satisifed, he closes his view of the digital world and walks away.

The technology is a demonstration system from Microsoft Research that can use any available surface to act as the interface for user interaction.  See a video and links here: http://research.microsoft.com/apps/video/?id=160684

As the technology shrinks and new ways of using the technology advance, expect to see the requirements for a surface dissappear, with the depth sensor working directly on images augmented to the users reality.  Sci-fi tech seeping into the real.


Applied artificial intelligence – speech recognition at Microsoft Research

Artificial intelligence is a field as wide as the endeavours of humankind itself.  One of the best ways to handle such a complex subject is to find niche areas that can be investigated in depth.  Then, at a later point, to abstract away from these areas to find patterns of common solution.

Speech recognition is one such area.  Microsoft Research has recently announced progress in building a general-purpose speech recognition capability – which does not require the hours of training typically needed to adapt the software to your way of speaking.

Their approach, presented during Interspeech 2011, breaks down the problem to use the finer-grained yet more numerous senones, rather than the traditional phonemes.  This has led to an improvement in word-recognition of more than 30%.

Read the article at Microsoft Research here: Speech Recognition Leaps Forward