Papers by Rami Kammoun

Copied to clipboard

Challenge:	Historically, TTS relied on classical methods that proved expensive in terms of data storage and often resulted in robotic-sounding output known as concatenative speech.
Approach:	They propose to extract a mono-speaker speech corpus from an online dictionary and use it to develop end-to-end TTS systems for the Tunisian dialect.
Outcome:	The proposed system is based on two approaches: training from scratch and transfer learning.