Contextual Expressive Text-to-Speech
This addresses the limitation of oversimplified style categories in expressive TTS, offering a more flexible approach for applications requiring nuanced speech generation.
The paper tackles the problem of generating expressive speech by introducing Contextual TTS, which uses textual context instead of fixed style labels to guide synthesis, and shows it produces high-quality expressive speech in synthetic and real-world scenarios.
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.