bshall / UniversalVocoding

A PyTorch implementation of "Robust Universal Neural Vocoding"
https://bshall.github.io/UniversalVocoding/
MIT License
238 stars 41 forks source link

generate_audio questions #19

Open Kerry0123 opened 4 years ago

Kerry0123 commented 4 years ago

hi,recently, I've been trying different mel preprocessing methods. mel is [-4, 4],audio stays the same(mulaw_encode and mulaw_decode stay the same). But, the generated audio contains a lot of noise, mel is normal.

original audio: image

generated audio: image

How can I deal with it? Looking forward for your response, thank you. @bshall