Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs

Understand

Neural audio super-resolution models are typically trained on low- and high-resolution audio signal pairs.

• Although these methods achieve highly accurate super-resolution if the acoustic characteristics of the input data are similar to those of the training data, challenges remain: the models suffer from quality degradation for out-of-domain data, and paired data are required for training.
• To address these problems, we propose Dual-CycleGAN, a high-quality audio super-resolution method that can utilize unpaired data based on two connected cycle consistent generative adversarial networks (CycleGAN).
• Our method decomposes the super-resolution method into domain adaptation and resampling processes to handle acoustic mismatch in the unpaired low- and high-resolution signals.