# Solos: A Dataset for Audio-Visual Music Analysis

arXiv: https://arxiv.org/abs/2006.07931 · HTML: https://mlsanity.com/paper/2006.07931/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [Language-Guided Audio-Visual Source Separation via Trimodal Consistency](https://mlsanity.com/paper/2303.16342/) (2023)
- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [Points2Sound: From mono to binaural audio using 3D point cloud scenes](https://mlsanity.com/paper/2104.12462/) (2021)
- [A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives](https://mlsanity.com/paper/2504.00837/) (2025)
- [MOSA: Music Motion with Semantic Annotation Dataset for Cross-Modal Music Processing](https://mlsanity.com/paper/2406.06375/) (2024)
- [Music source separation conditioned on 3D point clouds](https://mlsanity.com/paper/2102.02028/) (2021)
- [Video Object Segmentation-Aware Audio Generation](https://mlsanity.com/paper/2509.26604/) (2025)
- [Annotation-Free MIDI-to-Audio Synthesis via Concatenative Synthesis and Generative Refinement](https://mlsanity.com/paper/2410.16785/) (2024)

## Abstract (arXiv)

In this paper, we present a new dataset of music performance videos which can be used for training machine learning methods for multiple tasks such as audio-visual blind source separation and localization, cross-modal correspondences, cross-modal generation and, in general, any audio-visual self-supervised task. These videos, gathered from YouTube, consist of solo musical performances of 13 different instruments. Compared to previously proposed audio-visual datasets, Solos is cleaner since a big amount of its recordings are auditions and manually checked recordings, ensuring there is no background noise nor effects added in the video post-processing. Besides, it is, up to the best of our knowledge, the only dataset that contains the whole set of instruments present in the URMPciteURPM dataset, a high-quality dataset of 44 audio-visual recordings of multi-instrument classical music pieces with individual audio tracks. URMP was intented to be used for source separation, thus, we evaluate the performance on the URMP dataset of two different source-separation models trained on Solos. The dataset is publicly available at https://juanfmontesinos.github.io/Solos/