Does anyone have any links to good _in-depth_ discussions of this, or any books on it? (I actually prefer to have that big chunk of paper in front of me.) I already have a half-implemented phoneme-speaking program, so what I'm most interested in is english text-to-phoneme conversion and algorithms to make the speech more human-like. I suppose that last category would include timbre and the like, but I haven't really looked into it much yet.

Thanks, any help is appreciated.