Skip to main content
. Author manuscript; available in PMC: 2022 Jan 1.
Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2021 Jan 25;29:2058–2066. doi: 10.1109/taslp.2021.3054302

TABLE IV.

Number of Trainable Parameters for Different SR Models, where M Indicates Million

Number of Parameters
DNN-BWE 11.2 M
DNN-Cepstral 0.25 M
AudioUNet 70.9 M
TFNet 58.8 M
Proposed 10.2 M