# Uncovering Latent Style Factors for Expressive Speech Synthesis

arXiv: https://arxiv.org/abs/1711.00520 · HTML: https://mlsanity.com/paper/1711.00520/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2017.

## Built on by (most cited first, 5 of 5)

- [Word-Level Style Control for Expressive, Non-attentive Speech Synthesis](https://mlsanity.com/paper/2111.10173/) (2021)
- [GANtron: Emotional Speech Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2110.03390/) (2021)
- [LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example](https://mlsanity.com/paper/2110.04946/) (2021)
- [A Deep-Bayesian Framework for Adaptive Speech Duration Modification](https://mlsanity.com/paper/2107.04973/) (2021)
- [CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation](https://mlsanity.com/paper/2307.00020/) (2023)

## Abstract (arXiv)

Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of "style tokens" in Tacotron, a recently proposed end-to-end neural speech synthesis model. Using style tokens, we aim to extract independent prosodic styles from training data. We show that without annotation data or an explicit supervision signal, our approach can automatically learn a variety of prosodic variations in a purely data-driven way. Importantly, each style token corresponds to a fixed style factor regardless of the given text sequence. As a result, we can control the prosodic style of synthetic speech in a somewhat predictable and globally consistent way.