While acoustic expressiveness has long been studied in expressive
text-to-speech (ETTS), the inherent expressiveness in text lacks sufficient
attention, especially for ETTS of artistic works. In this paper, we introduce
StoryTTS, a highly ETTS dataset that contains rich expressiveness both in
acoustic and textual perspective, from the recording of a Mandarin storytelling
show. A systematic and comprehensive labeling framework is proposed for textual
expressiveness. We analyze and define speech-related textual expressiveness in
StoryTTS to include five distinct dimensions through linguistics, rhetoric,
etc. Then we employ large language models and prompt them with a few manual
annotation examples for batch annotation. The resulting corpus contains 61
hours of consecutive and highly prosodic speech equipped with accurate text
transcriptions and rich textual expressiveness annotations. Therefore, StoryTTS
can aid future ETTS research to fully mine the abundant intrinsic textual and
acoustic features. Experiments are conducted to validate that TTS models can
generate speech with improved expressiveness when integrating with the
annotated textual labels in StoryTTS.

我们介绍了 StoryTTS，一种包含丰富的声学和文本表现力的 ETTS 数据集，通过系统和全面的标注框架定义了五个维度的文本表现力，并使用大型语言模型进行批量注释，结果是包含 61 小时的连续且高度抑扬顿挫的语音，带有准确的文本转录和丰富的文本表现力注释。实验证明，当与 StoryTTS 中的文本标签集成时，TTS 模型能够生成具有改进表现力的语音。