On: Show HN: Neural text to speech with dozens of celebrity voices

[maxerickson]

It doesn't like spelling mistakes.

Ask it to say " The Aristoocrats!" with Gilbert Goddfried.

[echelon → maxerickson]

It's currently sourcing phonemes from a lookup table called CMUdict, which is constructed by Carnegie Mellon [1]. That database has 140,000 entries, but even so, you'd be surprised how many common words are omitted. And of course it is missing terms for things like "pokemon" and "fortnite", which I had to add myself.

I don't have generic grapheme -> phoneme/polyphone prediction, but that's something I look to add soon. In my literature review I didn't see anything in this space, so I was thinking I might have to come up with something novel.

[1] http://www.speech.cs.cmu.edu/cgi-bin/cmudict

[totetsu → echelon]

Espeak-ng also has extensive language rules to turn things like letter and abbreviations into pronounceable text https://github.com/espeak-ng/espeak-ng/blob/master/dictsourc... you can get it's ipa output with "speak-ng -q --ipa=3"

[nmstoker → echelon]

Espeak-ng has pretty decent English word to phoneme translation. You run it in the mode where it just outputs the IPA. The vocabulary can be extended too (as the coverage is good but far from perfect)