Google is collecting speech samples from speech impaired individuals, mainly ALS patients, to improve its ASR.
Project links: blog 1, blog 2, project home page
The project targets:
millions of people living with speech impairments caused by neurologic conditions such as stroke, ALS, multiple sclerosis, traumatic brain injuries and Parkinson’s.
It would be great if this project could collaborate with Google’s Euphonia project.
However, the Euphonia’s FAQ states:
Who can access my voice samples?
Only Google employees and affiliates working on Project Euphonia will have access to your recordings. Your recordings will not be available to anyone else unless you give us explicit permission.
Thus, if a collaboration (“affiliate”?) cannot be reached, I suggest we start collecting speech data of speech impaired individuals.
This data can do more than improve ASR, it can even assist in diagnosing the severity of a specific impairment and be used as a diagnosis tool