Abstract: Vocoder-based speech synthesis has become a promising technique to accommodate the demands of high-quality speech analysis, manipulation, and synthesis. However, most existing works focus on ...
This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS), with custom tweaks. datasets_root * LibriTTS * train-clean-100 * ...
A tiny Scottish island, 16 residents, a crumbling mansion, and two Australian dreamers - it's the perfect recipe for a riveting home renovation show. Interior designer Banjo Beale has become a firm ...
Astel has made a server version that works with both UTAU and OpenUtau. It may render faster than regular straycat. You can get it over here. I have made a new and ...
Abstract: This paper introduces V2Coder, a non-autoregressive vocoder based on hierarchical variational autoencoders (VAEs). The hierarchical VAE with hierarchically extended prior and approximate ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback