Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

Title: Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Authors: Yuxuan Wang, Daisy Stanton, Yu Zhang, RJ Skerry-Ryan, Eric Battenberg, Joel Shor, Ying Xiao, Fei Ren, Ye Jia, Rif A. Saurous
Published: 23rd March 2018 (Friday) @ 23:56:49
Link: http://arxiv.org/abs/1803.09017v1

Abstract

In this work, we propose “global style tokens” (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a rich set of significant results. The soft interpretable “labels” they generate can be used to control synthesis in novel ways, such as varying speed and speaking style -independently of the text content. They can also be used for style transfer, replicating the speaking style of a single audio clip across an entire long-form text corpus. When trained on noisy, unlabeled found data, GSTs learn to factorize noise and speaker identity, providing a path towards highly scalable but robust speech synthesis.

---

Style Tokens - Notes

• Seb: GSTs model channels
  • noise is one of the channels