I opened the article planning to dislike it, and I do dislike the man’s voice (the woman’s voice sounds quite good though), but then I thought about it. Sports announcers actually seem like a decent use for AI. I would imagine that it would be incredibly difficult to build decent announcers from pre-recorded voice lines… It’s heavily context-dependent, and this way it can even read out the team names, which I imagine are chosen by the teams. I think this could possibly work well. I don’t see how to create a system like this without AI
It’s not a generative model running on your graphics card coming up with novel speech to match the gamestate; it would never be fast enough (and you’re also using that card to, you know, run the graphics). They’re using machine learning to generate speech for their pre-written lines so that they can avoid hiring voice actors. I guess they didn’t want to try the old way of having whoever isn’t too busy in your office record the lines.
I opened the article planning to dislike it, and I do dislike the man’s voice (the woman’s voice sounds quite good though), but then I thought about it. Sports announcers actually seem like a decent use for AI. I would imagine that it would be incredibly difficult to build decent announcers from pre-recorded voice lines… It’s heavily context-dependent, and this way it can even read out the team names, which I imagine are chosen by the teams. I think this could possibly work well. I don’t see how to create a system like this without AI
It’s not a generative model running on your graphics card coming up with novel speech to match the gamestate; it would never be fast enough (and you’re also using that card to, you know, run the graphics). They’re using machine learning to generate speech for their pre-written lines so that they can avoid hiring voice actors. I guess they didn’t want to try the old way of having whoever isn’t too busy in your office record the lines.
Depending on how many variables/contexts there are in the lines, that could still be a combinatorial nightmare to record.
Yeah I’m not a fan of using AI voice actors but this doesn’t seem like a terrible use. It’s pretty useful for reactions to dynamic events.
Btw the male voice sounds fine to me. It’s the female voice that sounds obviously fake imo