Has anyone implemented vocal tract normalization in the framework of Sphinx3? Is there any source code downloadable?
Thanks,
Sphinxtrain supports vtln models and feature extraction in sphinxbase supports specifying vtln warp factor. There is no vtln estimation framework yet.
Log in to post a comment.
Has anyone implemented vocal tract normalization in the framework of Sphinx3?
Is there any source code downloadable?
Thanks,
Sphinxtrain supports vtln models and feature extraction in sphinxbase supports
specifying vtln warp factor. There is no vtln estimation framework yet.