This repository contains the Neural Network (NN) based Speech Synthesis System
developed at the Centre for Speech Technology Research (CSTR), University of
Edinburgh.
To build the toolkit: see ./INSTALL
. These instructions are valid for UNIX
systems including various flavors of Linux;
To run the example system builds, see egs/README.txt
As a first demo, please follow the scripts in egs/slt_arctic
Listen to synthetic speech samples from our demo voice.
- Create a personal fork of the [main Merlin repository] (https://github.com/CSTR-Edinburgh/merlin) in GitHub.
- Make your changes in a named branch different from
master
, e.g. you create a branchmy-new-feature
. - Generate a pull request through the Web interface of GitHub.
Post your questions, suggestions, and discussions to GitHub Issues.
If you publish work based on Merlin, please cite:
Zhizheng Wu, Oliver Watts, Simon King, "Merlin: An Open Source Neural Network Speech Synthesis System" in Proc. 9th ISCA Speech Synthesis Workshop (SSW9), September 2016, Sunnyvale, CA, USA.
Srikanth Ronanki, Zhizheng Wu, Oliver Watts, Simon King, "A Demonstration of the Merlin Open Source Neural Network Speech Synthesis System" in Proc. special demo session, 9th ISCA Speech Synthesis Workshop (SSW9), 2016, Sunnyvale, CA, USA.