JVS corpus: free Japanese multi-speaker voice corpus

TL;DR

This paper introduces the JVS corpus, a comprehensive Japanese multi-speaker voice dataset with 30 hours of diverse speech data from 100 speakers, aimed at advancing speech synthesis research.

Contribution

The paper presents the design and specifications of the new JVS corpus, expanding resources for multi-speaker and style-varied speech synthesis research.

Findings

Contains 30 hours of voice data from 100 speakers

Includes three speech styles: normal, whisper, and falsetto

Provides 22 hours of parallel normal voice data

Abstract

Thanks to improvements in machine learning techniques, including deep learning, speech synthesis is becoming a machine learning task. To accelerate speech synthesis research, we are developing Japanese voice corpora reasonably accessible from not only academic institutions but also commercial companies. In 2017, we released the JSUT corpus, which contains 10 hours of reading-style speech uttered by a single speaker, for end-to-end text-to-speech synthesis. For more general use in speech synthesis research, e.g., voice conversion and multi-speaker modeling, in this paper, we construct the JVS corpus, which contains voice data of 100 speakers in three styles (normal, whisper, and falsetto). The corpus contains 30 hours of voice data including 22 hours of parallel normal voices. This paper describes how we designed the corpus and summarizes the specifications. The corpus is available at our project page.