# Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis

arXiv: https://arxiv.org/abs/2304.06359 · HTML: https://mlsanity.com/paper/2304.06359/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2023.

## Built on by (most cited first, 1 of 1)

- [Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters](https://mlsanity.com/paper/2610.05575/) (2026)

## Abstract (arXiv)

Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in audiobooks. In this paper, we propose a context-aware coherent speaking style prediction method for audiobook speech synthesis. To predict the style embedding of the current utterance, a hierarchical transformer-based context-aware style predictor with a mixture attention mask is designed, considering both text-side context information and speech-side style information of previous speeches. Based on this, we can generate long-form speech with coherent style and prosody sentence by sentence. Objective and subjective evaluations on a Mandarin audiobook dataset demonstrate that our proposed model can generate speech with more expressive and coherent speaking style than baselines, for both single-sentence and multi-sentence test.