Libritts-p: A Corpus With Speaking Style And Speaker Identity Prompts For Text-to-speech And Style Captioning

Abstract

We introduce LibriTTS-P, a new corpus based on LibriTTS-R that includes utterance-level descriptions (i.e., prompts) of speaking style and speaker-level prompts of speaker characteristics. We employ a hybrid approach to construct prompt annotations: (1) manual annotations that capture human perceptions of speaker characteristics and (2) synthetic annotations on speaking style. Compared to existing English prompt datasets, our corpus provides more diverse prompt annotations for all speakers of LibriTTS-R. Experimental results for prompt-based controllable TTS demonstrate that the TTS model trained with LibriTTS-P achieves higher naturalness than the model using the conventional dataset. Furthermore, the results for style captioning tasks show that the model utilizing LibriTTS-P generates 2.5 times more accurate words than the model using a conventional dataset. Our corpus, LibriTTS-P, is available at https://github.com/line/LibriTTS-P.

Stats

• citations9
• S2 citations—
• github stars160
• HF likes0
• heat score11.91
• arxiv keykawamura2024libritts

Code

• line/LibriTTS-P—

Related papers

• Textrolspeech: A Text Style Control Speech Corpus With Codec Language Text-to-speech Models (2023)9.59
• Prompttts++: Controlling Speaker Identity In Prompt-based Text-to-speech Using Natural Language Descriptions (2023)9.23
• Libritts: A Corpus Derived From Librispeech For Text-to-speech (2019)20.79
• Instructtts: Modelling Expressive TTS In Discrete Latent Space With Natural Language Style Prompt (2023)0.00
• Promptasr For Contextualized ASR With Controllable Style (2023)8.35
• Promptstyle: Controllable Style Transfer For Text-to-speech With Natural Language Descriptions (2023)10.85
• Building Speech Corpus With Diverse Voice Characteristics For Its Prompt-based Representation (2024)0.00
• Expressive TTS Driven By Natural Language Prompts Using Few Human Annotations (2023)0.00