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.

翻译：尽管声学表现力在表现性文本转语音（ETTS）中已有深入研究，但文本中固有的表现力尚未得到充分关注，尤其在艺术作品的ETTS领域。本文介绍StoryTTS——一个从普通话故事讲述节目录音构建的高表现力ETTS数据集，其声学与文本层面均蕴含丰富表现力。针对文本表现力，我们提出系统全面的标注框架：通过语言学、修辞学等视角，分析并界定StoryTTS中与语音相关的文本表现力包含五个独立维度；继而采用大语言模型，辅以少量人工标注示例进行批量标注。最终语料包含61小时连续且韵律特征显著的语音，配备精准转写文本与丰富文本表现力标注。因此，StoryTTS有助于未来ETTS研究充分挖掘文本与声学特征中固有的丰富表现力。实验证明，结合StoryTTS标注的文本标签，TTS模型可生成表现力更优的语音。