Jodhpur : , Nov 29, 2009 – A team of innovators from the Indian Institute of Technology and All India Institute Of Medical Science in Jodhpur have developed low-cost Talking Gloves for people with speech impairment.The institutes announced Monday. The device employs Machine Learning (ML), Artificial Intelligence (AI), and Machine Learning (ML) principles to generate speech that is language independent and facilitate communication between normal people and mute people.
It can also be used to convert hand gestures into text and pre-recorded voices.
It makes it possible for people with disabilities to communicate effectively and is independent.According to the institutes, the device is less expensive than Rs 5,000.
“The language-independent speech generator device will bring people back into the mainstream of today’s global era without any language barriers.The device requires users to only learn one thing and they will be able verbally communicate in any language that is relevant to their knowledge,” stated Prof Sumit Kalra in a statement.
He said that the device can also be customized to produce a voice like the original voice of patients, which makes it seem more natural while using it.”
The in-built sensors allow the device to be worn on both hands.It generates electrical signals from hand movements and these are then received by a signal processing unit.
The signal processing unit uses the signal processing unit to compare the magnitude of the received electric signals with a number of pre-defined combinations.
These combinations of signals can then be translated into phonetics using AI and ML algorithms.
For example, the consonant or the vowel could be taken from Hindi phonetics.
Based on the comparison, a phonetic is assigned for the received electrical signals.
An audio transmitter generates an audio signal corresponding to the assigned phonetic.
It is based on stored data associated with vocal characteristics that has been trained and stored in a machine-learning unit.
The phonetic combination of vowels, consonants and vowels allows for the generation of audio signals that can be used to generate speech.
This allows mute people to communicate with each other.The speech synthesis technique used in the present subject matter relies on phonetics and is therefore independent of any language.
The team is working on improving the device’s durability, weight, responsiveness and ease-of use.
The product will be commercialized through a start up incubated at IIT Jodhpur.
rvt/vd #AIIMS #Jodhpur #create
.
