LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning

Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana
6/12/2024
eess.AScs.CLcs.LG

Official code: line/LibriTTS-P (161 stars, last commit 2024-06-13).

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.

View on arXivView PDF

Code Implementations(1)

line/LibriTTS-POfficial100%

LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning

1613Jun 7, 20242 years ago

Similar Papers

PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions

86% match1 repo862023

Scaling Rich Style-Prompted Text-to-Speech Datasets

82% match1 repo1662025

LibriQuote: A Speech Dataset of Fictional Character Utterances for Expressive Zero-Shot Speech Synthesis

81% match2025

Factor-Conditioned Speaking-Style Captioning

81% match2024

Natural language guidance of high-fidelity text-to-speech with synthetic annotations

80% match2024

CoLMbo: Speaker Language Model for Descriptive Profiling

80% match1 repo102025

Cite this paper

@article{kawamura2024librittsp,
  title  = {LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning},
  author = {Masaya Kawamura and Ryuichi Yamamoto and Yuma Shirahata and Takuya Hasumi and Kentaro Tachibana},
  year   = {2024},
  eprint = {2406.07969},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.07969v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.07969.svg)](https://codeofpaper.com/paper/2406.07969)

Discussion