Abstract: We propose a joint training scheme of an any-to-one voice conversion (VC) system with LPCNet to improve the speech naturalness, speaker similarity, and intelligibility of the converted ...
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 * ...
Abstract: This paper introduces V2Coder, a non-autoregressive vocoder based on hierarchical variational autoencoders (VAEs). The hierarchical VAE with hierarchically extended prior and approximate ...
This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. This was my master's ...
First announced all the way back in 2022, Behringer's UB-1 is an Oberheim-inspired microsynth based on the 3396/3397 chip design found in the company's Matrix synths. Since then, Behringer has ...
Behringer is no stranger to remaking classic synthesizers and selling them at much cheaper price points. However, this latest release may just take the budget-friendly cake. The company just ...
Back in 2023, Argentinian developers Martin Grieco and Rocío Gal shared a video showcasing a pastel-coloured prototype instrument named Nopia. That video went astronomically and unexpectedly viral, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback