Audio-Super-Resolution-Tensorflow2.0-TFiLM icon indicating copy to clipboard operation
Audio-Super-Resolution-Tensorflow2.0-TFiLM copied to clipboard

Published 20 hours ago • verified publisher icon leolya

About dataset

Open MichelleYang2017 opened this issue 3 years ago • 0 comments

I just got into this field. I want to ask some questions,

  1. Can the training data set only use one speaker's data?
  2. Each audio on the official website of vctk dataset is a FLAC generated by recording two microphones. It is two independent files. I would like to ask you how to process it. Do you use only one of the two microphones for format conversion, or do you use two microphones for special processing to synthesize one microphone data？ Thanks

MichelleYang2017 avatar Aug 11 '21 03:08 MichelleYang2017