Devices that can mimic a person’s voice while they are using them make it appear more authentic. A single lesson is all that is required for users to be able to converse in any language.
- A single lesson is all that is required for users to be able to converse in any language.
- The technology may also be customized to produce a voice that sounds more like the patient’s original voice.
- A firm incubated by IIT Jodhpur will market the created device, he said.
- The combination of vowels and consonants in phonetic phonetics generates speech.
“In today’s global era, the language-independent voice generation technology will bring people back into the mainstream without any linguistic barrier. In order to communicate in every language, users just need to master the gadget once,” said Sumit Kalra, Assistant Professor, Department of Computer Science and Engineering at IIT Jodhpur.
According to Kalra, the technology may also be customized to produce a voice that sounds more like the patient’s original voice.
There are two sets of sensors in the device: one set is worn on a user’s first hand, which includes sensors on their thumb, fingers, and wrist. In order to generate these electrical signals, the fingers, thumb, hand, and wrist must all move simultaneously. The second set of sensors, on the other hand, also generates electrical signals.
A signal processing unit receives these electrical signals. The signal processing unit compares the magnitude of the received electrical signals to a number of pre-defined magnitude combinations that have been recorded in a memory. These signals are transformed into phonetics matching to at least one consonant and a vowel utilizing AI and ML algorithms.
Hindi phonetics can be used for the consonant and the vowel in an example implementation.” According to Kalra, a phonetic is assigned to the electrical signals based on the comparison.
Assigned phonetic and learned data related to voice characteristics are stored in a machine learning unit, which generates an audio signal according to the assigned phonetic. The combination of vowels and consonants in phonetic phonetics generates speech, allowing mute people to speak vocally with others.
“The team is trying to improve the device’s durability, weight, responsiveness, and ease of use.” A firm incubated by IIT Jodhpur will market the created device, he said.