Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization.
Navonil MajumderChia-Yu HungDeepanway GhosalWei-Ning HsuRada MihalceaSoujanya PoriaPublished in: CoRR (2024)
Keyphrases
- music information retrieval
- audio content
- optimization algorithm
- information retrieval
- text mining
- diffusion process
- anisotropic diffusion
- text graphics
- information diffusion
- user preferences
- optimization problems
- evolutionary algorithm
- semantic information
- global optimization
- free text
- signal processing
- constrained optimization
- multiscale
- text to speech
- human language
- multimedia
- database