Mozualization: Crafting Music and Visual Representation with Multimodal AI
In this work, we introduce Mozualization, a music generation and editing tool that creates multi-style embedded music by integrating diverse inputs, such as keywords, images, and sound clips (e.g., segments from various pieces of music or even a playful cat's meow).
Authors
- Xinheng Song (ORCID: https://orcid.org/0000-0002-7930-4079)
- Eng Gee Lim (ORCID: https://orcid.org/0000-0003-0199-7386)
- Zhaolin Lu (ORCID: https://orcid.org/0009-0008-7775-5352)
- Yu Liu (ORCID: https://orcid.org/0000-0003-0226-1311)
- Min Chen (ORCID: https://orcid.org/0000-0002-3122-6788)
- Lixiang Zhao (ORCID: https://orcid.org/0000-0001-6181-1673)
- Lingyun Yu (ORCID: https://orcid.org/0000-0002-3152-2587)
- Wenpu Xu (ORCID: https://orcid.org/0009-0005-3014-2901)
- Haiwen Song
Institutions
- Beijing Institute of Technology (CN)
- Xi’an Jiaotong-Liverpool University (CN)
Publication Details
- Published
- 2025-04-25
- DOI
- https://doi.org/10.1145/3706599.3719686
- Primary Topic
- Music and Audio Processing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Ministry of Education of the People's Republic of China
- Beijing Institute of Technology
- Fundamental Research Funds for the Central Universities