Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis

TL;DR

This paper introduces a hierarchical context-aware framework with a novel training strategy for Mandarin speech synthesis, significantly enhancing expressiveness and naturalness by modeling broader contextual information.

Contribution

It proposes a hierarchical context encoder and a knowledge distillation training strategy to better capture speech style from wider context in Mandarin synthesis.

Findings

Improved naturalness and expressiveness in synthesized speech.

Significant gains demonstrated through objective and subjective evaluations.

Abstract

Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we propose a hierarchical framework to model speaking style from context. A hierarchical context encoder is proposed to explore a wider range of contextual information considering structural relationship in context, including inter-phrase and inter-sentence relations. Moreover, to encourage this encoder to learn style representation better, we introduce a novel training strategy with knowledge distillation, which provides the target for encoder training. Both objective and subjective evaluations on a Mandarin lecture dataset demonstrate that the proposed method can significantly improve the naturalness and expressiveness of the synthesized speech.