2 code implementations • 8 Nov 2022 • Junhyeok Lee, Seungu Han, Hyunjae Cho, Wonbin Jung
Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth waveform from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis.
4 code implementations • 17 Jun 2022 • Seungu Han, Junhyeok Lee
Conventionally, audio super-resolution models fixed the initial and the target sampling rates, which necessitate the model to be trained for each pair of sampling rates.
3 code implementations • 6 Apr 2021 • Junhyeok Lee, Seungu Han
In this work, we introduce NU-Wave, the first neural audio upsampling model to produce waveforms of sampling rate 48kHz from coarse 16kHz or 24kHz inputs, while prior works could generate only up to 16kHz.