CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages

TL;DR

CLaMP 3 introduces a unified, contrastive learning framework that aligns multiple music modalities with multilingual text, enabling cross-modal and cross-lingual music retrieval with strong generalization and state-of-the-art results.

Contribution

It presents a novel unified approach combining contrastive learning and retrieval-augmented generation for universal music information retrieval across modalities and languages.

Findings

Achieves state-of-the-art performance on MIR tasks

Demonstrates strong cross-lingual generalization

Provides new datasets and benchmarks for future research

Abstract

CLaMP 3 is a unified framework developed to address challenges of cross-modal and cross-lingual generalization in music information retrieval. Using contrastive learning, it aligns all major music modalities--including sheet music, performance signals, and audio recordings--with multilingual text in a shared representation space, enabling retrieval across unaligned modalities with text as a bridge. It features a multilingual text encoder adaptable to unseen languages, exhibiting strong cross-lingual generalization. Leveraging retrieval-augmented generation, we curated M4-RAG, a web-scale dataset consisting of 2.31 million music-text pairs. This dataset is enriched with detailed metadata that represents a wide array of global musical traditions. To advance future research, we release WikiMT-X, a benchmark comprising 1,000 triplets of sheet music, audio, and richly varied text descriptions. Experiments show that CLaMP 3 achieves state-of-the-art performance on multiple MIR tasks, significantly surpassing previous strong baselines and demonstrating excellent generalization in multimodal and multilingual music contexts.