CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models
Wu, Shangda, Wang, Yashan, Yuan, Ruibin, Guo, Zhancheng, Tan, Xu, Zhang, Ge, Zhou, Monan, Chen, Jing, Mu, Xuefeng, Gao, Yuejie, Dong, Yuanliang, Liu, Jiafeng, Li, Xiaobing, Yu, Feng, Sun, Maosong
–arXiv.org Artificial Intelligence
Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (Musical Instrument Digital Interface) for music information retrieval. CLaMP 2, pre-trained on 1.5 million ABC-MIDI-text triplets, includes a multilingual text encoder and a multimodal music encoder aligned via contrastive learning. By leveraging large language models, we obtain refined and consistent multilingual descriptions at scale, significantly reducing textual noise and balancing language distribution. Our experiments show that CLaMP 2 achieves state-of-the-art results in both multilingual semantic search and music classification across modalities, thus establishing a new standard for inclusive and global music information retrieval.
arXiv.org Artificial Intelligence
Oct-17-2024
- Country:
- South America > Argentina (0.04)
- North America
- United States
- Rhode Island (0.04)
- Washington > King County
- Seattle (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- Canada > British Columbia
- United States
- Europe
- Greece (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Netherlands > South Holland
- Delft (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Italy > Lombardy
- Milan (0.04)
- Asia
- South Korea > Seoul
- Seoul (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- India > Karnataka
- Bengaluru (0.04)
- China > Beijing
- Beijing (0.04)
- South Korea > Seoul
- Genre:
- Research Report (0.64)
- Industry:
- Media > Music (1.00)
- Leisure & Entertainment (1.00)
- Education > Curriculum
- Subject-Specific Education (0.34)
- Technology: