Cue Point Estimation using Object Detection

TL;DR

This paper introduces a novel computer vision approach using object detection transformers to automatically estimate cue points in music tracks, significantly improving accuracy without analyzing musical content directly.

Contribution

It presents a new method leveraging pre-trained object detection transformers and a large annotated dataset for cue point estimation in music, outperforming previous techniques.

Findings

Higher precision in cue point detection compared to prior methods

No need for low-level musical feature analysis

Strong adherence to musical phrasing

Abstract

Cue points indicate possible temporal boundaries in a transition between two pieces of music in DJ mixing and constitute a crucial element in autonomous DJ systems as well as for live mixing. In this work, we present a novel method for automatic cue point estimation, interpreted as a computer vision object detection task. Our proposed system is based on a pre-trained object detection transformer which we fine-tune on our novel cue point dataset. Our provided dataset contains 21k manually annotated cue points from human experts as well as metronome information for nearly 5k individual tracks, making this dataset 35x larger than the previously available cue point dataset. Unlike previous methods, our approach does not require low-level musical information analysis, while demonstrating increased precision in retrieving cue point positions. Moreover, our proposed method demonstrates high adherence to phrasing, a type of high-level music structure commonly emphasized in electronic dance music. The code, model checkpoints, and dataset are made publicly available.