Conditional Music Generation
Conditional music generation aims to create music tailored to specific inputs, such as text descriptions, melodies, or even dance videos, enhancing human-computer interaction in music composition. Current research heavily utilizes deep learning models, including transformers, diffusion models, and generative adversarial networks (GANs), often employing novel architectures to improve controllability, audio quality, and efficiency. This field is significant for its potential to automate music creation, assist musicians in production, and advance our understanding of music representation and generation, impacting both artistic expression and music technology.
Papers
On The Open Prompt Challenge In Conditional Audio Generation
Ernie Chang, Sidd Srinivasan, Mahi Luthra, Pin-Jie Lin, Varun Nagaraja, Forrest Iandola, Zechun Liu, Zhaoheng Ni, Changsheng Zhao, Yangyang Shi, Vikas Chandra
In-Context Prompt Editing For Conditional Audio Generation
Ernie Chang, Pin-Jie Lin, Yang Li, Sidd Srinivasan, Gael Le Lan, David Kant, Yangyang Shi, Forrest Iandola, Vikas Chandra