Synthesized speech coming directly from brain activities is a somewhat new field of science, but it seems to be advancing at a pace unheard-of in scientific discovery. That is what the post is all about.
The sources for this post have been sitting in my “ideas pot” for almost a year now. It’s time to make it into a post. Click on the image above to see the entire article.
In my early career I was involved in the beginning stages of voice recognition. Back then the team I was on was trying to accomplish it with 4-bit processors, now we have basically a thousand times that capacity in our smartphones. Getting computers to recognize speech has gone eons beyond my crude studies. Personally, voice recognition has made my life many times better than before it was readily available.
Being deaf, basically means I was cut off from the hearing world when I left my front door. I could plead with those I encountered to accept my paper and pencil to write what they were saying but amazingly few would volunteer to do that. I can only imagine what it would be like for someone who can’t talk! But, it seems help for them is not too far off the scientific horizon.
There are a number of university research projects working to be able to produce synthesized speech directly from brain activity!
The primary work in this field has been done at the Mayo Clinic. Some of the many recipients will be those with epilepsy but it will provide communications techniques for many more than that if it proves practical. I assume that this technology will be limited only to those who think in English and know word structured languages?
Being able to interact with those around you is a significant part of life. Obstacles that prevent that communications cause serious isolation and depression. I can personally attest to that.