Text-aware and Context-aware Expressive Audiobook Speech Synthesis

Dake Guo¹, Xinfa Zhu¹, Liumeng Xue², Yongmao Zhang¹, Wenjie Tian¹, Lei Xie^{1 1}Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China ²School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China

1. Abstract

Recent advances in text-to-speech have significantly improved the expressiveness of synthetic speech. However, a major challenge remains in generating speech that captures the diverse styles exhibited by professional narrators in audiobooks, without relying on manually labeled data or reference speech. To address this problem, we propose a text-aware and context-aware (TACA) style modeling approach for expressive audiobook speech synthesis. We first establish a text-aware style space to cover diverse styles via contrastive learning with the supervision of the speech-style space. Meanwhile, we adopt a context encoder to incorporate cross-sentence information and the style embedding obtained from text. Finally, we introduce the context encoder to two typical TTS models, including VITS-based TTS and language model-based TTS. Experimental results demonstrate that our proposed approach can effectively capture diverse styles and coherent prosody, and thus improves naturalness and expressiveness in audiobook speech synthesis.

Figure 2. Text-aware Context-aware VITS (TACA-VITS)	Figure 3. Text-aware Context-aware Language Model (TACA-LM)

2. Demos

References: