r505Matt said:
I don't know anything about speech synthesis, so I didn't make any comments on it. I was more interested in talking about speech recognition and gesture/emotion recognition, both of which I believe are possible for Milo. Though, my argument works against myself, and while I might know a bit about speech recognition, I am by no means an expert. But since we're on speech synthesis, I don't think that's what they're trying to do with Milo (yet). I do think that what Milo is saying is scripted, but I don't think the experience is scripted. That can go towards the illusion thing Molyneux talks about, and that's okay so long as the experience itself is immersive as a result. This is obvious but we won't really know until it's released or shortly beforehand. |
I’m currently working in a company that deals heavily with voice recognition, and have worked directly with it in my past; although I am far from an expert in it, and my focus is in a completely different segment of the company (because they’re moving away from voice based systems). Our sales team will brag about a 75% recognition rate to new clients for a voice based system for a very simple call-flow because of how few systems can achieve that success level; and this requires more processing power than you could dedicate to the task on the XBox 360 and still have a game running at the same time. If you’re wondering, human levels of recognition are in the 97.5% range.
Bleeding edge voice recognition is so primitive it makes the worst Wiimote Waggle look amazingly precise.