Privacy campaigners need not worry. AlterEgo works by using ‘subvocalisations’ — tiny, imperceptible movements in the jaw each time you say a word with your tongue to just yourself
The Hush Post: How about a devise that lets you hear the thoughts of the person sitting across? But there is a catch, only if the words are being used at a sub-vocalised level! What does sub-vocalised mean? It means, for example one is angry at his boss and has muttered something with a closed-mouth, the device will decipher the words.
And the credit to do this goes to an Indian-origin American researcher at Massachusetts Institute of Technology (MIT).
Arnav Kapur, an Indian American’s ‘AlterEgo’ headset is a brilliant conception, something that reads the sub-vocalised mind to such an accurate extent that one can exactly write down what one wanted to say but didn’t.
However, the MIT website makes its clear in its frequently asked questions: “This device cannot read your mind… The system does not have any direct and physical access to brain activity, and therefore cannot read a user’s thoughts.”
It says that privacy campaigners need not worry. AlterEgo works by using ‘subvocalisations’ — tiny, imperceptible movements in the jaw each time you say a word with your tongue to just yourself.
The device in its present form looks like a curved bone hooked to one ear that touches the jaw on the chin and under the lower lip.
While the idea of turning sub-vocalisations to speech is not new, for Kapur’s team the challenge was to identify the locations on the face where the most reliable vibrations can be picked up.
They initially worked with 16 sensors. Now they are able to get accuracy with four sensors, increasing hopes of a miniature device that users won’t mind wearing.
After the device picks up signals, a computer that has been trained to recognise and convert them back to words is put to work. But AlterEgo doesn’t transmit the words to the listener as ordinary ‘over the air’ sound waves. Some more tech magic happens now as the words are conveyed to the listener’s mind through ‘bone conduction’. Instead of making air molecules vibrate all around, the vibration is sent through direct contact with the listener’s jawbone.
The big advantage of these two technologies — reading sub-vocalisations and bone-conduction is that it will enable voice communication without sound. For instance, in a crowded place, two persons will be able to talk to each other without shouting.
It also has another potential. For example, through AlterEgo’s technology, you could ask questions soundlessly, and get a voice reply only in your ears. You can work in the most crowded of places with full privacy.
Currently, Kapur’s team claims an accuracy of 92 per cent, which is slightly less than the performance of Google’s voice transcription. But Kapur says it will perform better in time.