# Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control

arXiv: https://arxiv.org/abs/2309.13509 · HTML: https://mlsanity.com/paper/2309.13509/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2023.

## Built on by (most cited first, 7 of 7)

- [Scaling Rich Style-Prompted Text-to-Speech Datasets](https://mlsanity.com/paper/2503.04713/) (2025)
- [LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning](https://mlsanity.com/paper/2406.07969/) (2024)
- [CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech](https://mlsanity.com/paper/2506.02863/) (2025)
- [Voice Attribute Editing with Text Prompt](https://mlsanity.com/paper/2404.08857/) (2024)
- [Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control](https://mlsanity.com/paper/2409.17452/) (2024)
- [Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts](https://mlsanity.com/paper/2503.01947/) (2025)
- [AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style](https://mlsanity.com/paper/2603.11482/) (2026)

## Abstract (arXiv)

In text-to-speech, controlling voice characteristics is important in achieving various-purpose speech synthesis. Considering the success of text-conditioned generation, such as text-to-image, free-form text instruction should be useful for intuitive and complicated control of voice characteristics. A sufficiently large corpus of high-quality and diverse voice samples with corresponding free-form descriptions can advance such control research. However, neither an open corpus nor a scalable method is currently available. To this end, we develop Coco-Nut, a new corpus including diverse Japanese utterances, along with text transcriptions and free-form voice characteristics descriptions. Our methodology to construct this corpus consists of 1) automatic collection of voice-related audio data from the Internet, 2) quality assurance, and 3) manual annotation using crowdsourcing. Additionally, we benchmark our corpus on the prompt embedding model trained by contrastive speech-text learning.