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. In this work, we
introduce the Text-Predicted Global Style Token (TP-GST) architecture, which
treats GST combination weights or style embeddings as "virtual" speaking style
labels within Tacotron. TP-GST learns to predict stylistic renderings from text
alone, requiring neither explicit labels during training nor auxiliary inputs
for inference. We show that, when trained on a dataset of expressive speech,
our system generates audio with more pitch and energy variation than two
state-of-the-art baseline models. We further demonstrate that TP-GSTs can
synthesize speech with background noise removed, and corroborate these analyses
with positive results on human-rated listener preference audiobook tasks.
Finally, we demonstrate that multi-speaker TP-GST models successfully factorize
speaker identity and speaking style. We provide a website with audio samples
for each of our findings.

本文介绍了一种名为 “Text-Predicted Global Style Token” 的结构，能够使用 GST 技术，仅通过文本预测生成带有语音样式的合成语音，无需显式标签或辅助输入，并证明其能生成比两种基线模型更多具有音高和能量变化的音频，并且能够成功地分离说话者身份和语音风格。