[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:04444] YANG vocoder


Hi,

While Prof. Hideki Kawahara was a visiting researcher at Google, he developed a new vocoder with my colleague Yannis Agiomyrgiannakis.

Today Google open-sourced it under the Apache License 2.0.  You can find the code at
https://github.com/google/yang_vocoder.

Please feel free to use it and contribute to the development.  Thanks Yannis for his effort to make it publicly available.

Cheers,

Heiga


P.S. Here is the description from its README.

YANG VOCODER: Yet-ANother-Generalized VOCODER

Yet another vocoder that is not STRAIGHT.

This project is a state-of-the-art vocoder that parameterizes the speech signal into a parameterization that is amenable to statistical manipulation.

The VOCODER was developed by Hideki Kawahara during his internship at Google.

Hideki Kawahara (kawahara@xxxxxxxxxxxxxxxxxxxx)
Yannis Agiomyrgiannakis (agios@xxxxxxxxxx)
Heiga Zen (heigazen@xxxxxxxxxx)

DISCLAIMER:

This is not an official Google product. The code is provided as is and it is  written to be accessible by experts in the field.


--
---------------------------------------
Heiga ZEN (in Japanese)
Byung Ha CHUN (in Korean)
<heigazen@xxxxxxxxxx>

Follow-Ups
[hts-users:04445] Re: YANG vocoder, Xingyu Na