It is basically the vocoder suggested in:
G. Degottex, P. Lanchantin, and M. Gales, "A Pulse Model in Log-domain for a Uniform Synthesizer," in Proc. 9th Speech Synthesis Workshop (SSW9), 2016.
Please see the headers of analysis.py and synthesis.py files as well as the functions documentation for more details.
In the root directory, simply run:
$ make test
Copyright(C) 2016 Engineering Department, University of Cambridge, UK.
The code in this repository is released under the Apache License, Version 2.0. Please see LICENSE.md for more details.
Author: Gilles Degottex [email protected]