Storytts: A Highly Expressive Text-to-speech Dataset With Rich Textual Expressiveness Annotations

Abstract

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 acoust

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyliu2024storytts

Related papers

• Instructtts: Modelling Expressive TTS In Discrete Latent Space With Natural Language Style Prompt (2023)0.00
• Textrolspeech: A Text Style Control Speech Corpus With Codec Language Text-to-speech Models (2023)9.59
• Speechcraft: A Fine-grained Expressive Speech Dataset With Natural Language Description (2024)7.81
• Computational Narrative Understanding For Expressive Text-to-speech (2025)0.00
• Emospeech: A Corpus Of Emotionally Rich And Contextually Detailed Speech Annotations (2024)0.00
• Mscenespeech: A Multi-scene Speech Dataset For Expressive Speech Synthesis (2024)0.00
• EE-TTS: Emphatic Expressive TTS With Linguistic Information (2023)2.26
• Gtr-voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis (2024)0.00