Learning Bandwidth Expansion Using Perceptually-Motivated Loss

ICASSP, May 2019

Berthy Feng, Zeyu Jin,
Jiaqi Su, Adam Finkelstein

We introduce a perceptually motivated approach to bandwidth expansion for speech. Our method pairs a new 3-way split variant of the FFTNet neural vocoder structure with a perceptual loss function, combining objectives from both the time and frequency domains. Mean opinion score tests show that it outperforms baseline methods from both domains, even for extreme bandwidth expansion.

Paper preprint
Listen to audio clips from our experiments.

Berthy Feng, Zeyu Jin, Jiaqi Su, and Adam Finkelstein.
"Learning Bandwidth Expansion Using Perceptually-Motivated Loss."
ICASSP, May 2019.

@inproceedings{Feng:2019:LBE,
   author = "Berthy Feng and Zeyu Jin and Jiaqi Su and Adam Finkelstein",
   title = "Learning Bandwidth Expansion Using Perceptually-Motivated Loss",
   booktitle = "ICASSP",
   year = "2019",
   month = may
}