Although this is the experience prototype pretty much complete, it is so painfully close to working ‘for real’ (as in, consistently, unlike the examples in this video) that I feel a little depressed about it all now! This works a lot more than I ever dreamed it would in the beginning, and I know that things would only improve if it was made commercial: if I had more control over the software and the way it makes it’s decisions, and some real knowledge of microphones and speech recognition then this would be a real world product. The post-translation editing that I am doing really ought to be embedded in the program itself, and there are so many other aspects of the software that I really want to be able to ‘get at’ that could make this work properly!

I have to remember that in the offset, I didn’t think I’d be able to get any of it working, but to now be so close to it working completely, and being of so much use to the user group, I truly wish it was a complete product. I suppose with that realisation, I have surely completed what I set out to achieve in the physical build… which is nothing but good news.

All this was to find out if I was going to have to do anything clever to demonstrate the subtitling during the film about the application and it’s potential. Unfortunately it looks like I am going to have to do something pretty cunning.