This workshop introduces the core concepts of modern deep learning based speech synthesis and allows users to learn-by-doing.
We will get hands-on experience with synthesising, training and analysing these research-derived models.
By the end, we will have a good understanding of how to make machines talk in a very human-like way.
- 1st part: Introduction
- 2nd part: Synthesise (Practical)
- 3rd part: Understanding
- 4th part:Training (Practical)
- 5th part: Analysis/Evaluation (Practical)
- 6th part: Where next?
Session length: 1.5 hours
