# Enriched Music Representations with Multiple Cross-modal Contrastive Learning

arXiv: https://arxiv.org/abs/2104.00437 · HTML: https://mlsanity.com/paper/2104.00437/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2021.

## Built on by (most cited first, 10 of 10)

- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [MuLan: A Joint Embedding of Music Audio and Natural Language](https://mlsanity.com/paper/2208.12415/) (2022)
- [Codified audio language modeling learns useful representations for music information retrieval](https://mlsanity.com/paper/2107.05677/) (2021)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions](https://mlsanity.com/paper/2107.13782/) (2021)
- [Contrastive Audio-Language Learning for Music](https://mlsanity.com/paper/2208.12208/) (2022)
- [Holistic Representation Learning for Multitask Trajectory Anomaly Detection](https://mlsanity.com/paper/2311.01851/) (2023)
- [Learning music audio representations via weak language supervision](https://mlsanity.com/paper/2112.04214/) (2021)
- [Improving Music Performance Assessment with Contrastive Learning](https://mlsanity.com/paper/2108.01711/) (2021)
- [CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations](https://mlsanity.com/paper/2608.30974/) (2026)

## Abstract (arXiv)

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such as the audio, interactions between users and songs, or associated genre metadata. Recently, contrastive learning has led to representations that generalize better compared to traditional supervised methods. In this paper, we present a novel approach that combines multiple types of information related to music using cross-modal contrastive learning, allowing us to learn an audio feature from heterogeneous data simultaneously. We align the latent representations obtained from playlists-track interactions, genre metadata, and the tracks' audio, by maximizing the agreement between these modality representations using a contrastive loss. We evaluate our approach in three tasks, namely, genre classification, playlist continuation and automatic tagging. We compare the performances with a baseline audio-based CNN trained to predict these modalities. We also study the importance of including multiple sources of information when training our embedding model. The results suggest that the proposed method outperforms the baseline in all the three downstream tasks and achieves comparable performance to the state-of-the-art.