search

yangdongchao / AcademiCodec

AcademiCodec: An Open Source Audio Codec Model for Academic Research
596 stars 81 forks source link

Data Augmentation in Soundstream #19

Open cyanbx opened 1 year ago

cyanbx commented 1 year ago

Hi, thanks for your great work. I notice that the NSynthDataset used in SoundStream contains data augmentation by adding two audio waveforms, which does not appear in Encodec. I wonder where is this technique proposed, and have you found that it helps the audio quality? Thanks.

yangdongchao commented 1 year ago

Hi, thanks for your great work. I notice that the NSynthDataset used in SoundStream contains data augmentation by adding two audio waveforms, which does not appear in Encodec. I wonder where is this technique proposed, and have you found that it helps the audio quality? Thanks.

Yes, it can gain small improvement, but not significant. You can try it.