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

Source: [Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control](<https://www.sota2.com/research/paper/68fa70ab1e209131cea4c571>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:46:58.939Z

Authors: Aya Watanabe, Shinnosuke Takamichi, Yuki Saito, Wataru Nakata, Detai Xin, Hiroshi Saruwatari

Published: 2023-09-24T00:15:31.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.13509>)

[PDF](<https://arxiv.org/pdf/2309.13509.pdf>)