Closed hhhuazi closed 1 year ago
Thanks for your interest. Can you please elaborate your question?
I'm sorry I didn't clarify my issue. In your other paper, StarGAN-VC++mentioned in section 2.2: Emission Leakage by Speaker Embedding, using ESD dataset to train the model. I would like to ask if the labels used during training are based on speakers or accounts?
Hello, your job is very interesting. Regarding the issue of emotional leakage, may I ask if you labeled the issue of emotional leakage with accents or speakers?