JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus

TL;DR

The paper introduces the jaCappella corpus, a new Japanese a cappella vocal ensemble dataset with diverse genres and voice parts, designed for vocal separation and synthesis research, and demonstrates its challenging nature through experiments.

Contribution

It provides a publicly available, genre-diverse Japanese a cappella corpus with multiple voice parts, filling a gap in vocal ensemble datasets for research.

Findings

The corpus is challenging for vocal ensemble separation tasks.

It includes 35 songs across genres like jazz and enka.

The dataset is suitable for vocal synthesis and separation research.

Abstract

We construct a corpus of Japanese a cappella vocal ensembles (jaCappella corpus) for vocal ensemble separation and synthesis. It consists of 35 copyright-cleared vocal ensemble songs and their audio recordings of individual voice parts. These songs were arranged from out-of-copyright Japanese children's songs and have six voice parts (lead vocal, soprano, alto, tenor, bass, and vocal percussion). They are divided into seven subsets, each of which features typical characteristics of a music genre such as jazz and enka. The variety in genre and voice part match vocal ensembles recently widespread in social media services such as YouTube, although the main targets of conventional vocal ensemble datasets are choral singing made up of soprano, alto, tenor, and bass. Experimental evaluation demonstrates that our corpus is a challenging resource for vocal ensemble separation. Our corpus is available on our project page (https://tomohikonakamura.github.io/jaCappella_corpus/).