We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps).
This repository implements various generative data augmentation strategies using stable diffusion to create synthetic datasets, aimed at enhancing classification tasks. The key packages and their ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results