EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal

TL;DR

The EMVD dataset provides a comprehensive collection of extreme vocal techniques in heavy metal, enabling research in vocal distortion classification and analysis with diverse recordings from multiple singers.

Contribution

This paper introduces the first extensive dataset of extreme metal vocal techniques, including detailed distortion taxonomy and baseline classification results.

Findings

Dataset contains 760 audio clips from 27 singers.

Deep learning model achieves promising classification accuracy.

Dataset supports research in vocal technique analysis.

Abstract

In this paper, we introduce the Extreme Metal Vocals Dataset, which comprises a collection of recordings of extreme vocal techniques performed within the realm of heavy metal music. The dataset consists of 760 audio excerpts of 1 second to 30 seconds long, totaling about 100 min of audio material, roughly composed of 60 minutes of distorted voices and 40 minutes of clear voice recordings. These vocal recordings are from 27 different singers and are provided without accompanying musical instruments or post-processing effects. The distortion taxonomy within this dataset encompasses four distinct distortion techniques and three vocal effects, all performed in different pitch ranges. Performance of a state-of-the-art deep learning model is evaluated for two different classification tasks related to vocal techniques, demonstrating the potential of this resource for the audio processing community.