search

CSTR-Edinburgh / magphase

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.
Apache License 2.0
78 stars 31 forks source link

Is variable frame rate essential for quality? #8

Open lmaxwell opened 6 years ago

lmaxwell commented 6 years ago

To my understanding, magphase vocoder can also use fixed frame rate. I guess the advantage of using variable frame rate is computational efficiency and quality. If my understanding is correct, I'm interested in which benefits more. Because If fixed frame rate can be used, it is easier to integrate the vocoder into any existing TTS frameworks.

felipeespic commented 6 years ago

Hi @lmaxwell , I am sorry for the delay on replying.

At the beginning, when I started MagPhase, I did some experiments using constant frame rate (by interpolating the variable frame rate features), which didn't achieve comparable quality with the variable frame rate version. However, right now I am working on making a high quality interpolator to convert from variable to constant frame rate (and vice versa), which seems to deliver the same quality. So, I will push the constant frame rate version of MagPhase soon.

Thanks for the comment.

lmaxwell commented 6 years ago

that's awesome, I'll try it in my work

felipeespic commented 6 years ago

Hi, I just pushed the constant frame version (v2.0).