A New Dataset for Amateur Vocal Percussion Analysis

TL;DR

This paper introduces a new dataset of amateur vocal percussion recordings with annotations, aiming to improve automatic mapping of vocal imitations to percussion instruments and enhance rhythm prototyping tools.

Contribution

The study presents a novel dataset of 9,780 annotated vocal percussion samples from amateurs and evaluates baseline onset detection algorithms on this data.

Findings

Baseline algorithms show varying performance on amateur vocal percussion data.

The dataset enables better understanding of amateur vocal percussion patterns.

Results highlight challenges in automatic detection for non-expert vocalizations.

Abstract

The imitation of percussive instruments via the human voice is a natural way for us to communicate rhythmic ideas and, for this reason, it attracts the interest of music makers. Specifically, the automatic mapping of these vocal imitations to their emulated instruments would allow creators to realistically prototype rhythms in a faster way. The contribution of this study is two-fold. Firstly, a new Amateur Vocal Percussion (AVP) dataset is introduced to investigate how people with little or no experience in beatboxing approach the task of vocal percussion. The end-goal of this analysis is that of helping mapping algorithms to better generalise between subjects and achieve higher performances. The dataset comprises a total of 9780 utterances recorded by 28 participants with fully annotated onsets and labels (kick drum, snare drum, closed hi-hat and opened hi-hat). Lastly, we conducted baseline experiments on audio onset detection with the recorded dataset, comparing the performance of four state-of-the-art algorithms in a vocal percussion context.