1 code implementation • 22 Nov 2022 • Moshe Mandel, Or Tal, Yossi Adi
We optimize the model using both time and frequency domain loss functions.
Ranked #1 on Bandwidth Extension on VCTK
1 code implementation • 22 Jun 2022 • Or Tal, Moshe Mandel, Felix Kreuk, Yossi Adi
By conducting a series of controlled experiments, we observe the influence of different phonetic content models as well as various feature-injection techniques on enhancement performance, considering both causal and non-causal models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3