[PDF][PDF] Investigating the Effects of Noisy and Reverberant Speech in Text-to-Speech Systems.

D Ayllón, HA Sánchez-Hevia, C Figueroa… - …, 2019 - isca-archive.org
The quality of the voices synthesized by a Text-to-Speech (TTS) system depends on the
quality of the training data. In real case scenario of TTS personalization from user's voice …