Open ronanki opened 7 years ago
Another tutorial from Columbia University, hope it will help
@Jackiexiao Do you know how to visit "Merlin Instructions and Troubleshooting" in your shared tutorial?
Sorry, I don't know, but you can try to send an email to Erica Cooper for help
We are using docs on Merlin repo for documentation at cstr-edinburgh.github.io/merlin.
As of now, there's very limited information on how to build voices -- but we'll keep updating it. We very much appreciate any contribution towards documentation as well -- which can be a pull request in form of Markdown README file.
How will this tutorial take place? it will be a practical session with computers (should we be equipped with personal computer with Merlin already configured) or it will be a set of presentations only? Thanks
Just presentations - it's only 3 hours long in total, so doing a practical session doesn't really work.
Simon
-- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.
The tutorial is now available freely for everyone - videos and slides are here:
http://www.speech.zone/courses/one-off/merlin-interspeech2017/
Enjoy!
Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit
This tutorial will combine the theory and practical application of Deep Neural Networks (DNNs) for Text-to-Speech (TTS). It will illustrate how DNNs are rapidly advancing the performance of all areas of TTS, including waveform generation and text processing, using a variety of model architectures. We will link the theory to implementation with the Open Source Merlin toolkit.
If you are interested in attending the tutorial, please register along with Interspeech 2017.