# Automatic Music Sample Identification with Multi-Track Contrastive Learning

arXiv: https://arxiv.org/abs/2510.11507 · HTML: https://mlsanity.com/paper/2510.11507/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Audio-based Musical Version Identification: Elements and Challenges](https://mlsanity.com/paper/2109.02472/) (2021)
- [SampleMatch: Drum Sample Retrieval by Musical Context](https://mlsanity.com/paper/2208.01141/) (2022)
- [Supervised contrastive learning from weakly-labeled audio segments for musical version matching](https://mlsanity.com/paper/2502.16936/) (2025)
- [Discogs-VI: A Musical Version Identification Dataset Based on Public Editorial Metadata](https://mlsanity.com/paper/2410.17400/) (2024)
- [Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset](https://mlsanity.com/paper/2502.06364/) (2025)
- [Refining music sample identification with a self-supervised graph neural network](https://mlsanity.com/paper/2506.14684/) (2025)

## Built on by (most cited first, 1 of 1)

- [On the Human and Computer Alignment of Attribute-Based Music Matches](https://mlsanity.com/paper/2609.00987/) (2026)

## Abstract (arXiv)

Sampling, the technique of reusing pieces of existing audio tracks to create new music content, is a very common practice in modern music production. In this paper, we tackle the challenging task of automatic sample identification, that is, detecting such sampled content and retrieving the material from which it originates. To do so, we adopt a self-supervised learning approach that leverages a multi-track dataset to create positive pairs of artificial mixes, and design a novel contrastive learning objective. We show that such method significantly outperforms previous state-of-the-art baselines, that is robust to various genres, and that scales well when increasing the number of noise songs in the reference database. In addition, we extensively analyze the contribution of the different components of our training pipeline and highlight, in particular, the need for high-quality separated stems for this task.