You're currently viewing an old version of this dataset. To see the current version, click here.

Global Style Tokens

Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis system, to uncover expressive factors of variation in speaking style.

Data and Resources

This dataset has no data

Cite this as

Daisy Stanton, Yuxuan Wang, RJ Skerry-Ryan (2024). Dataset: Global Style Tokens. https://doi.org/10.57702/vb6621tl

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Daisy Stanton
More Authors
Yuxuan Wang
RJ Skerry-Ryan
Homepage https://google.github.io/tacotron/publications/