JukeBox: A Multilingual Singer Recognition Dataset

TL;DR

JukeBox introduces a multilingual singing voice dataset to evaluate and improve speaker recognition systems, highlighting challenges and effects of gender and language on performance across singing and spoken voices.

Contribution

The paper presents the first large-scale, labeled singing voice dataset for speaker recognition, enabling research beyond traditional spoken voice data.

Findings

Speaker recognition is more challenging on singing voice than spoken voice.

Gender and language significantly affect recognition accuracy.

Models trained on spoken voice perform poorly on singing voice.

Abstract

A text-independent speaker recognition system relies on successfully encoding speech factors such as vocal pitch, intensity, and timbre to achieve good performance. A majority of such systems are trained and evaluated using spoken voice or everyday conversational voice data. Spoken voice, however, exhibits a limited range of possible speaker dynamics, thus constraining the utility of the derived speaker recognition models. Singing voice, on the other hand, covers a broader range of vocal and ambient factors and can, therefore, be used to evaluate the robustness of a speaker recognition system. However, a majority of existing speaker recognition datasets only focus on the spoken voice. In comparison, there is a significant shortage of labeled singing voice data suitable for speaker recognition research. To address this issue, we assemble \textit{JukeBox} - a speaker recognition dataset with multilingual singing voice audio annotated with singer identity, gender, and language labels. We use the current state-of-the-art methods to demonstrate the difficulty of performing speaker recognition on singing voice using models trained on spoken voice alone. We also evaluate the effect of gender and language on speaker recognition performance, both in spoken and singing voice data. The complete \textit{JukeBox} dataset can be accessed at http://iprobe.cse.msu.edu/datasets/jukebox.html.