You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Great work! I want to ask if you have tried using mel as input? If mel is used as input and the same bitrate is maintained (e.g. frameshift=256, encoder downsampled by 3 times), will the performance of the model change significantly?
The text was updated successfully, but these errors were encountered:
Great work! I want to ask if you have tried using mel as input? If mel is used as input and the same bitrate is maintained (e.g. frameshift=256, encoder downsampled by 3 times), will the performance of the model change significantly?
From my perspective, it seems feasible to input Mel spectrograms and maintain the same or even higher compression ratios without significantly degrading performance. However, I am puzzled as to why most current codecs do not adopt this approach. What is the rationale behind this decision?
Great work! I want to ask if you have tried using mel as input? If mel is used as input and the same bitrate is maintained (e.g. frameshift=256, encoder downsampled by 3 times), will the performance of the model change significantly?
The text was updated successfully, but these errors were encountered: