EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal
This provides a new dataset for the audio processing community to study extreme vocal techniques, but it is incremental as it focuses on a specific domain without broader methodological advances.
The authors introduced the Extreme Metal Vocals Dataset, comprising 760 audio excerpts totaling about 100 minutes from 27 singers, to tackle the problem of classifying extreme vocal distortion techniques in heavy metal music, and they evaluated a state-of-the-art deep learning model on two classification tasks to demonstrate its potential.
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.