Contextual Expressive Text-to-Speech

TL;DR

This paper introduces Contextual TTS, a new approach that synthesizes expressive speech based on textual context rather than predefined style labels, improving naturalness and expressiveness.

Contribution

It proposes the CTTS task setting, constructs a synthetic dataset, and develops a framework that leverages context for more natural and expressive speech synthesis.

Findings

Framework generates high-quality expressive speech from context

Effective on both synthetic and real-world data

Outperforms label-based style control methods

Abstract

The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and emotions, which over-simplifies the problem by classifying styles and emotions into a fixed number of pre-defined categories. In this paper, we introduce a new task setting, Contextual TTS (CTTS). The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. Thus, in the CTTS task, we propose to utilize such context to guide the speech synthesis process instead of relying on explicit labels of styles and emotions. To achieve this task, we construct a synthetic dataset and develop an effective framework. Experiments show that our framework can generate high-quality expressive speech based on the given context both in synthetic datasets and real-world scenarios.