Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization
Authors
- Navonil Majumder (ORCID: https://orcid.org/0000-0002-1449-617X)
- Soujanya Poria (ORCID: https://orcid.org/0000-0001-6924-7931)
- Wei-Ning Hsu (ORCID: https://orcid.org/0000-0001-5546-5217)
- Rada Mihalcea (ORCID: https://orcid.org/0000-0002-0767-6703)
- Deepanway Ghosal (ORCID: https://orcid.org/0000-0002-3858-4449)
- Chia-Yu Hung (ORCID: https://orcid.org/0009-0006-5252-0763)
Institutions
- Singapore University of Technology and Design (SG)
- University of Michigan (US)