A new software, developed by computer scientists at Carnegie Mellon University (CMU) at Pittsburgh, usa, will aid computers to recognise speech through lip reading. "The new software, NLips, will reduce the error rate of speech recognition software in noisy environments," says Alex Waibel of the CMU. Normal speech recognition software is 60 per cent successful when the surroundings are noisy, while the new software is 85 per cent successful. NLips, like most speech recognition systems, breaks down speech into sound chunks called phonemes. But significantly, the new software combines information from lip movements and uses computer-mounted cameras to record lip sequences ( New Scientist , Vol 163, No 2199).
We are a voice to you; you have been a support to us. Together we build journalism that is independent, credible and fearless. You can further help us by making a donation. This will mean a lot for our ability to bring you news, perspectives and analysis from the ground so that we can make change together.
Comments are moderated and will be published only after the site moderator’s approval. Please use a genuine email ID and provide your name. Selected comments may also be used in the ‘Letters’ section of the Down To Earth print edition.