14 DAY TRIAL // After numerous programs developed by companies in order to innovate the fingerprint identification technology, here comes the turn of the voice recognition technology.
The Carnegie-Mellon University (CMU) revealed that its team of engineers has come up with a new and revolutionary chip architecture that is able to speed up speech recognition by ten times over PC dedicated processors.
However, this new chip architecture is specialized exclusively on speech recognition and, according to Electronics Weekly, the US Homeland Security department is said to be very enthusiastic about CMU's program because it will also help the specialists to translate any given audio data encrypted in several not so spoken languages.
If we come to think about this, the chip may also be used during war, as it will 'translate' any given message, disregarding the language used, if someone will add special software to go with CMU's chip architecture.
"Whether running an enterprise-class voice call-in centre or decoding individual words on a cell phone, all of today's serious speech recognizers exist as software running on some processor. That's terribly limiting," said Professor Rob A. Rutenbar, who leads the In Silico Vox project at CMU. "Moving these computations directly into silicon means we can perform recognition dramatically faster, cheaper, and better for both commercial and homeland security tasks."