A futuristic institute aims to preserve (and recreate) people's voices using artificial intelligence.
Researchers involved in the 'voice bank' initiative hope to change the lives of all people who find themselves losing their voices as a result of illness or accidents. Losing your voice isn't exactly like having a momentary lowering of the sound or a hoarseness. The loss of the voice is in part the loss of identity.
It all started from a collaboration between Northeastern University of Boston and the Vowels D.. Providing those who lose the use of speech a way to retain a sense of their identity after throat cancer or degenerative disease is important. This project will allow them to "speak" using a synthetic form very similar to their own voice.
It is the first center of this type, and will be led by prof. Rupal Patel, founder and CEO of VocaliD.
The company already offers such a service for individuals, Patel says, but many people lack equipment of sufficient quality to properly sample vocals. Building a “voice bank” allows future patients to keep their voice when they still have the chance.
"Often patients come to us at the last moment," He says. “They do not have enough time to keep their voice because they are at the mercy of illness, operations and more. And it's very frustrating ”.
The voice bank
The result was the collaboration with Northeastern to spread the technology to the public. The heart of the project is the Voice Preservation Clinic, a center where patients at risk of losing their voice can register it to protect it.
The approach is much more complicated than those based on traditional speech syntheses: a machine learning algorithm reconstructs ligatures, phonemes and even rhythm in relation to breathing. In a special booth, small stories, poems, or conversations on different themes are recorded. Someone even joked about how to lose your voice, a self-deprecating way of dealing with great fear.
“What it takes is about two or three hours of speaking. From these recordings our artificial intelligence is able to generate a voice engine that has the same sound. It is like returning the voice to those who have lost it ”.
The regenerated voice can be used as speech synthesis to speak by converting written texts, and can be integrated tomorrow with software that generates words, images or actions from mental paths.
A very rapid improvement
Technology, Patel says, is improving rapidly, and will soon be able to reproduce speech that is indistinguishable from human speech.
The team will also be able to "age" the voice to adapt it to the age of the person, while it is not yet possible to "grow" a boy's voice by transforming it into an adult.