With all the work that's been happening recently to research and revive vintage speech synthesizers, I've been hearing more and more of forment, diphone, unit selection etc speech synths. Can someone explain to me in simple terms what these types of speech synth are? I get neural, it's machine learning for human sounding speech.
=> More informations about this toot | More toots from TwoThousandStu@fwoof.space
text/geminiThis content has been proxied by September (3851b).