Annotation of Soft Onsets in String Ensemble Recordings

TL;DR

This paper investigates the challenges of annotating soft onsets in string recordings, compares human and algorithm performance, and provides a new dataset to advance research in this niche area of onset detection.

Contribution

It introduces a comprehensive analysis of inter-annotator agreement, extends an annotation consistency algorithm, and releases a new dataset for soft onset research in string instrument recordings.

Findings

Higher musical experience correlates with better annotation agreement and detection performance.

Fingering changes and cello onsets are particularly difficult for both humans and algorithms.

The publicly available dataset supports future research in soft onset detection and annotation practices.

Abstract

Onset detection is the process of identifying the start points of musical note events within an audio recording. While the detection of percussive onsets is often considered a solved problem, soft onsets-as found in string instrument recordings-still pose a significant challenge for state-of-the-art algorithms. The problem is further exacerbated by a paucity of data containing expert annotations and research related to best practices for curating soft onset annotations for string instruments. To this end, we investigate inter-annotator agreement between 24 participants, extend an algorithm for determining the most consistent annotator, and compare the performance of human annotators and state-of-the-art onset detection algorithms. Experimental results reveal a positive trend between musical experience and both inter-annotator agreement and performance in comparison with automated systems. Additionally, onsets produced by changes in fingering as well as those from the cello were found to be particularly challenging for both human annotators and automatic approaches. To promote research in best practices for annotation of soft onsets, we have made all experimental data associated with this study publicly available. In addition, we publish the ARME Virtuoso Strings dataset, consisting of over 144 recordings of professional performances of an excerpt from Haydn's string quartet Op. 74 No. 1 Finale, each with corresponding individual instrumental onset annotations.