Hal points out there is plenty to do with your mind when your body’s not working and there’s assistive technology (and other people) to help us along the way.

People sometimes tell me right to my face that they’d rather die than use a wheelchair, a ventilator, be paralyzed, blind, or lose whatever function it is they are scared of losing, both because they can’t picture solutions to practical problems, and because they “don’t want to be a burden”. If that describes you, go read some of the information at Not Dead Yet:

It’s the ultimate form of discrimination to offer people with disabilities help to die without having offered real options to live.

In his post, Hal says,

I hope that when the time comes, I will choose life. ALS kills only motor neurons, which carry signals to the muscles. The senses are intact. And most patients retain at least some vestige of control over a few muscles, which with modern technology can offer a surprisingly effective mode of communication. Stephen Hawking, the world’s longest surviving ALS patient at over 40 years since diagnosis, is said to be able to type at ten words per minute by twitching a cheek muscle. I hope to be able to read, browse the net, and even participate in conversations by email and messaging. Voice synthesizers allow local communications, and I am making use of a free service for ALS patients which will create a synthetic model of my own natural voice, for future use. I may even still be able to write code, and my dream is to contribute to open source software projects even from within an immobile body. That will be a life very much worth living.

Right on, Hal. You’re fierce! I’m glad you’re determined to not die! Fuck that noise! It makes me proud to see your post!

Free open source speech synthesis software: FestVox I don’t know if this is useful for voice banking and SGDs, but it sounds like a good possibility for people who have ALS.

And the OneSwitch.org.uk site may also be a good resource.

Let’s not forget the totally crucial bit, politics and activism for social change, such as The Community Choice Act which would enable more people to live independently in their own homes.

Most acoustic models used by ‘Open Source’ speech recognition (or Speech-to-Text) engines are ‘Closed Source’. They do not give you access to the speech audio and transcriptions (i.e. the speech corpus) used to create the acoustic model.

The reason for this is that Free and Open Source (‘FOSS’) projects are required to purchase large speech corpora with restrictive licensing. Although there are a few instances of small FOSS speech corpora that could be used to create acoustic models, the vast majority of corpora (especially large corpora best suited to building good acoustic models) must be purchased under restrictive licenses.