This paper presents FastFit, a novel neural vocoder architecture that
re...
In neural text-to-speech (TTS), two-stage system or a cascade of separat...
Most neural vocoders employ band-limited mel-spectrograms to generate
wa...
We propose Universal MelGAN, a vocoder that synthesizes high-fidelity sp...
We propose Jointly trained Duration Informed Transformer (JDI-T), a
feed...
This thesis introduces the sequence to sequence model with Luong's atten...