[ad_1]
The results are not flawless. Although the system accurately captures the distinctive sound of a person's voice and is often easy to understand, sometimes the synthesizer produces truncated words. It is still much better than the previous approaches that did not try to reproduce the vocal tract. Scientists are also testing denser electrodes at the brain interface, as well as more sophisticated machine learning, which could improve overall accuracy. It would work ideally with any person, even if it can not train the system before using it in practice.
This effort may take some time and no roadmap is established at this stage. The goal, at least, is clear: researchers want to revive the voices of people with ALS, Parkinson's and other conditions where the loss of speech is normally irreversible. If this happened, it could dramatically improve communication for patients (who might be forced to use much slower methods today) and help them feel more connected to society.
[ad_2]
Source link