search

maum-ai / assem-vc

Official Code for Assem-VC @ICASSP2022
https://mindslab-ai.github.io/assem-vc/
BSD 3-Clause "New" or "Revised" License
265 stars 38 forks source link

One-to-Many #22

Open xxoospring opened 3 years ago

xxoospring commented 3 years ago

can it use as an "one-to-many" conversion model? I have few unpaired datasets, 1 hour for each, 1k+ sentences, SNR > 40dB. I want to know if I can make this project as an "one-to-many" or said one-vs-rest model?

wookladin commented 3 years ago

Hi, I didn't understand the "one-vs-rest model" you said. Could you explain more about the "one-vs-rest model" you mean?

You can use this project as an "any-to-many" or "many-to-many" conversion model, which enables any speakers' voice as source audio. However, you can only convert to speakers who are in the training dataset. Hence, I think you can surely use this repository as a one-to-many conversion model with your dataset.