Search Results for author:
Found 2 papers, 0 papers with code
FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTs
This paper presents FastFit, a novel neural vocoder architecture that replaces the U-Net encoder with multiple short-time Fourier transforms (STFTs) to achieve faster generation rates without sacrificing sample quality.
JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment
We propose Jointly trained Duration Informed Transformer (JDI-T), a feed-forward Transformer with a duration predictor jointly trained without explicit alignments in order to generate an acoustic feature sequence from an input text.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
