Re:Neural Codec Language Models Are Zero-Shot Text to Speech...
by woodson on Friday January 06, 2023 @01:25AM
(#34271628)
Is it just me, or does the spoken content not correspond with the written prompt in many cases? Though, I’m sure it’s just a problem with matching the right file with the text in the HTML and not a TTS problem.
[ Parent
| on HN ]
Re:Neural Codec Language Models Are Zero-Shot Text to Speech...
by babakd on Friday January 06, 2023 @01:31AM
(#34271657)
The speaker prompt is the sample speaker voice reading a random text, that’s one piece that the model uses as input. The second column corresponds to the human speaker reading the text (ground truth) The two next columns are baseline and VALL-E producing text-to-speech respectively, given the first column and only the text as input.
Re:Neural Codec Language Models Are Zero-Shot Text to Speech...
by cookingrobot on Friday January 06, 2023 @01:34AM
(#34271673)
The first column of audio is just a sample of that person reading different text. That’s what the model gets to hear to learn what they sound like, before trying to speak the text in their voice.