Obout downsampling implementation.

auspicious3000 / SpeechSplit

Unsupervised Speech Decomposition Via Triple Information Bottleneck

http://arxiv.org/abs/2004.11284

MIT License

636 stars 92 forks source link

Obout downsampling implementation. #58

Closed yangdongchao closed 2 years ago

yangdongchao commented 2 years ago

In your experiments, you choose downsampling frame number from 192 to 24. After that, you recover time resolution by repeat_interleave operation. So my question is if we donot use downsampling, the performance will decrease? In your experiments, the upsampling operation is followwing downsampling operation. So it aims at discard some information?

auspicious3000 commented 2 years ago

downsampling is an information bottleneck