no code implementations • 29 Feb 2024 • Takaaki Saeki, Gary Wang, Nobuyuki Morioka, Isaac Elias, Kyle Kastner, Andrew Rosenberg, Bhuvana Ramabhadran, Heiga Zen, Françoise Beaufays, Hadar Shemtov
Without any transcribed speech in a new language, this TTS model can generate intelligible speech in >30 unseen languages (CER difference of <10% to ground truth).
6 code implementations • 8 Oct 2020 • Jonathan Shen, Ye Jia, Mike Chrzanowski, Yu Zhang, Isaac Elias, Heiga Zen, Yonghui Wu
This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor.