Speech Recognition – white elephant?

== Summary ==

Image via Wikipedia

My carpal tunnel’s resurfaced recently, making typing a pain. Writing is already something I find hard to do.

“Writing is easy. All you do is stare at a blank sheet of paper until drops of blood form on your forehead.” – Gene Fowler

Replace forehead with wrists and you’ve got my experience. So I’ve tried ergonomic keyboards, different mice, experimental seating or desk arrangements.

Invariably it all boils down to not spending too much time at a keyboard. I miss my trusty Thinkpad R52 – IBM made the best keyboards for those laptops and I probably did some of my best writing on my old laptop.

So I’ve been experimenting with WSR or Windows Speech Recognition. It’s come a long way from its beginnings; I remember when just leaving your microphone on could lead to all sorts of gibberish on your document. Now, the word recognition is far more accurate and dictation is more intuitive. The WSR tutorial is also very well-done and I found it quite enjoyable going through the training module.

I am dictating this blogpost right now, and it certainly gives me a new perspective on the whole composition process.  Yes, it’s not exactly an error-free process, and I do find that I have to slow down and correct mistakes manually. 

But I think that dictation is a means of writing that is more fluid, achieving a style closer to how you would actually speak.  I think it is a great tool for speechwriters and perhaps even poets.  Most important, it gives my wrists a rest.

I don’t think it will completely replace typing for me, but so far it’s proving to be fun.  Who knows what the future might bring?  Perhaps speech recognition might actually come to the mobile phone and save me hours off transcribing notes.  Maybe then I’ll start to like interviewing.


Reblog this post [with Zemanta]

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.