2 code implementations • 1 Jun 2023 • Hubert Siuzdak
Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain.
Ranked #6 on Speech Synthesis on LibriTTS
no code implementations • 31 Mar 2022 • Hubert Siuzdak, Piotr Dura, Pol van Rijn, Nori Jacoby
Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms.